Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0945. Min Range: -8.0945
Max Act: 8.0945. Min Act: -0.1700
Data Index: 3204457 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.6570. Min Act: -0.1700
Data Index: 491755 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.5320. Min Act: -0.1700
Data Index: 3335853 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.5632. Min Act: -0.1700
Data Index: 1974324 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.5632. Min Act: -0.1700
Data Index: 659322 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.5007. Min Act: -0.1700
Data Index: 2197296 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.4382. Min Act: -0.1700
Data Index: 4780582 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.2507. Min Act: -0.1700
Data Index: 5297640 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.2507. Min Act: -0.1700
Data Index: 3034284 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.2195. Min Act: -0.1700
Data Index: 7892301 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.1570. Min Act: -0.1700
Data Index: 4546261 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.1570. Min Act: -0.1700
Data Index: 378150 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.1570. Min Act: -0.1700
Data Index: 1107881 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.1257. Min Act: -0.1700
Data Index: 7353570 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.0945. Min Act: -0.1700
Data Index: 5954407 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.0945. Min Act: -0.1700
Data Index: 5699683 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.0945. Min Act: -0.1700
Data Index: 5690100 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.0945. Min Act: -0.1700
Data Index: 6153023 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.0632. Min Act: -0.1700
Data Index: 8297546 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0945. Min Range: -8.0945
Max Act: 7.0632. Min Act: -0.1700
Data Index: 3739711 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19