Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5353. Min Range: -7.5353
Max Act: 7.5353. Min Act: -0.1700
Data Index: 4853921 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5353. Min Range: -7.5353
Max Act: 7.3478. Min Act: -0.1700
Data Index: 1392572 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5353. Min Range: -7.5353
Max Act: 7.1603. Min Act: -0.1700
Data Index: 6321091 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5353. Min Range: -7.5353
Max Act: 7.0978. Min Act: -0.1700
Data Index: 2463871 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5353. Min Range: -7.5353
Max Act: 7.0978. Min Act: -0.1700
Data Index: 7277167 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5353. Min Range: -7.5353
Max Act: 7.0666. Min Act: -0.1700
Data Index: 4978786 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5353. Min Range: -7.5353
Max Act: 7.0666. Min Act: -0.1700
Data Index: 4351135 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5353. Min Range: -7.5353
Max Act: 7.0353. Min Act: -0.1700
Data Index: 7597044 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.9416. Min Act: -0.1700
Data Index: 2664995 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.9103. Min Act: -0.1700
Data Index: 5906042 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.8791. Min Act: -0.1700
Data Index: 8378200 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.9103. Min Act: -0.1700
Data Index: 2006807 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.9103. Min Act: -0.1700
Data Index: 5022085 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.8791. Min Act: -0.1700
Data Index: 399693 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.8478. Min Act: -0.1700
Data Index: 8664381 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.8478. Min Act: -0.1700
Data Index: 6269233 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.8478. Min Act: -0.1700
Data Index: 7047702 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.8166. Min Act: -0.1700
Data Index: 2873260 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.8478. Min Act: -0.1700
Data Index: 656456 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5353. Min Range: -7.5353
Max Act: 6.7853. Min Act: -0.1700
Data Index: 1195978 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19