Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.8126. Min Act: -0.1700
Data Index: 8307916 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.7489. Min Act: -0.1700
Data Index: 3109925 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.7329. Min Act: -0.1700
Data Index: 7809076 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.7329. Min Act: -0.1700
Data Index: 7809074 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.7009. Min Act: -0.1700
Data Index: 3845438 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.7009. Min Act: -0.1700
Data Index: 578994 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.7169. Min Act: -0.1700
Data Index: 7443836 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.7169. Min Act: -0.1700
Data Index: 5573422 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.7009. Min Act: -0.1700
Data Index: 6062918 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6849. Min Act: -0.1700
Data Index: 8430325 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6689. Min Act: -0.1700
Data Index: 578993 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6689. Min Act: -0.1700
Data Index: 6084256 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6689. Min Act: -0.1700
Data Index: 1159761 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6368. Min Act: -0.1700
Data Index: 7074498 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6528. Min Act: -0.1700
Data Index: 6709382 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6528. Min Act: -0.1700
Data Index: 1736988 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6689. Min Act: -0.1700
Data Index: 7443839 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6528. Min Act: -0.1700
Data Index: 7443838 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6528. Min Act: -0.1700
Data Index: 1165491 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8126. Min Range: -2.8126
Max Act: 2.6528. Min Act: -0.1700
Data Index: 5389696 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19