Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1379. Min Range: -5.1379
Max Act: 5.1379. Min Act: -0.1700
Data Index: 4526306 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1379. Min Range: -5.1379
Max Act: 5.1066. Min Act: -0.1700
Data Index: 5383934 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1379. Min Range: -5.1379
Max Act: 5.1066. Min Act: -0.1700
Data Index: 7811904 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1379. Min Range: -5.1379
Max Act: 5.0441. Min Act: -0.1700
Data Index: 3783679 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1379. Min Range: -5.1379
Max Act: 5.0129. Min Act: -0.1700
Data Index: 8772989 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9816. Min Act: -0.1700
Data Index: 1617363 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1379. Min Range: -5.1379
Max Act: 5.0129. Min Act: -0.1700
Data Index: 2176302 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9504. Min Act: -0.1700
Data Index: 8189123 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9816. Min Act: -0.1700
Data Index: 743190 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9191. Min Act: -0.1700
Data Index: 5061857 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9504. Min Act: -0.1700
Data Index: 4786288 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9191. Min Act: -0.1700
Data Index: 6855467 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9191. Min Act: -0.1700
Data Index: 1533554 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9504. Min Act: -0.1700
Data Index: 5029376 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.8879. Min Act: -0.1700
Data Index: 4840954 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.9191. Min Act: -0.1700
Data Index: 5958589 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.8879. Min Act: -0.1700
Data Index: 4425836 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.8566. Min Act: -0.1700
Data Index: 5124688 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.8566. Min Act: -0.1700
Data Index: 2124871 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1379. Min Range: -5.1379
Max Act: 4.8879. Min Act: -0.1700
Data Index: 5571253 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19