Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.3187. Min Act: -0.1700
Data Index: 4107573 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.2402. Min Act: -0.1700
Data Index: 4216306 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.2087. Min Act: -0.1700
Data Index: 6861100 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.2087. Min Act: -0.1700
Data Index: 8172840 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1616. Min Act: -0.1700
Data Index: 2264544 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1301. Min Act: -0.1700
Data Index: 4530491 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1301. Min Act: -0.1700
Data Index: 7214489 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1458. Min Act: -0.1700
Data Index: 2737843 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1301. Min Act: -0.1700
Data Index: 4013373 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1301. Min Act: -0.1700
Data Index: 8317148 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1143. Min Act: -0.1700
Data Index: 2168602 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1301. Min Act: -0.1700
Data Index: 6036606 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1301. Min Act: -0.1700
Data Index: 212523 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1143. Min Act: -0.1700
Data Index: 2635732 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1143. Min Act: -0.1700
Data Index: 3647653 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.0986. Min Act: -0.1700
Data Index: 7863814 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.1143. Min Act: -0.1700
Data Index: 3647655 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.0670. Min Act: -0.1700
Data Index: 4760115 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.0986. Min Act: -0.1700
Data Index: 2635735 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3187. Min Range: -3.3187
Max Act: 3.0986. Min Act: -0.1700
Data Index: 4008348 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19