Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4946 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0136. Min Range: -6.0136
Max Act: 6.0136. Min Act: -0.1700
Data Index: 783665 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.9511. Min Act: -0.1700
Data Index: 60946 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.9198. Min Act: -0.1700
Data Index: 1529047 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8886. Min Act: -0.1700
Data Index: 6575398 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8573. Min Act: -0.1700
Data Index: 7210265 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8573. Min Act: -0.1700
Data Index: 1182738 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8573. Min Act: -0.1700
Data Index: 4889071 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8573. Min Act: -0.1700
Data Index: 7865107 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8261. Min Act: -0.1700
Data Index: 1501831 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8261. Min Act: -0.1700
Data Index: 7968324 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.8261. Min Act: -0.1700
Data Index: 4066353 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7948. Min Act: -0.1700
Data Index: 3112065 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 3553346 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 2501972 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 1529045 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7323. Min Act: -0.1700
Data Index: 3632675 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 1199770 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 766372 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 5914108 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0136. Min Range: -6.0136
Max Act: 5.7011. Min Act: -0.1700
Data Index: 3873 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19