Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.1194. Min Range: -11.1194
Max Act: 11.1194. Min Act: -0.1700
Data Index: 5113998 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.8694. Min Act: -0.1700
Data Index: 6890115 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.6194. Min Act: -0.1700
Data Index: 2257465 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.6819. Min Act: -0.1700
Data Index: 1803770 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.5569. Min Act: -0.1700
Data Index: 8354027 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.4319. Min Act: -0.1700
Data Index: 7359459 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.4944. Min Act: -0.1700
Data Index: 2983731 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.3694. Min Act: -0.1700
Data Index: 7298522 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.3069. Min Act: -0.1700
Data Index: 5730843 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.1819. Min Act: -0.1700
Data Index: 5939834 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.2444. Min Act: -0.1700
Data Index: 1774406 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.2444. Min Act: -0.1700
Data Index: 1318815 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.2444. Min Act: -0.1700
Data Index: 2112247 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.2444. Min Act: -0.1700
Data Index: 2396863 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.2444. Min Act: -0.1700
Data Index: 3428244 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.1819. Min Act: -0.1700
Data Index: 7624219 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.2444. Min Act: -0.1700
Data Index: 7868926 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.1819. Min Act: -0.1700
Data Index: 1616986 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.1819. Min Act: -0.1700
Data Index: 4741118 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1194. Min Range: -11.1194
Max Act: 10.1819. Min Act: -0.1700
Data Index: 1168580 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19