Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.1395. Min Range: -6.1395
Max Act: 6.1395. Min Act: -0.1700
Data Index: 3947716 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1395. Min Range: -6.1395
Max Act: 6.0145. Min Act: -0.1700
Data Index: 8743469 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1395. Min Range: -6.1395
Max Act: 6.0145. Min Act: -0.1700
Data Index: 645146 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.9208. Min Act: -0.1700
Data Index: 7576231 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.9208. Min Act: -0.1700
Data Index: 7074514 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.9208. Min Act: -0.1700
Data Index: 2500142 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8895. Min Act: -0.1700
Data Index: 965542 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8895. Min Act: -0.1700
Data Index: 3247893 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8895. Min Act: -0.1700
Data Index: 1417808 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8895. Min Act: -0.1700
Data Index: 7974274 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8583. Min Act: -0.1700
Data Index: 760163 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8583. Min Act: -0.1700
Data Index: 2541617 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8583. Min Act: -0.1700
Data Index: 1521450 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8895. Min Act: -0.1700
Data Index: 506157 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8895. Min Act: -0.1700
Data Index: 6512540 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8583. Min Act: -0.1700
Data Index: 3382017 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8270. Min Act: -0.1700
Data Index: 1591233 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8270. Min Act: -0.1700
Data Index: 2839281 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.8583. Min Act: -0.1700
Data Index: 2950376 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1395. Min Range: -6.1395
Max Act: 5.7958. Min Act: -0.1700
Data Index: 3091325 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19