Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4909 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.8420. Min Act: -0.1700
Data Index: 2514733 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.7483. Min Act: -0.1700
Data Index: 7186452 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.6858. Min Act: -0.1700
Data Index: 8092667 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.6858. Min Act: -0.1700
Data Index: 806917 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.6858. Min Act: -0.1700
Data Index: 3501132 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.6858. Min Act: -0.1700
Data Index: 3403717 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.5295. Min Act: -0.1700
Data Index: 1673727 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.5295. Min Act: -0.1700
Data Index: 7481048 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4983. Min Act: -0.1700
Data Index: 3288200 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4983. Min Act: -0.1700
Data Index: 6051544 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4983. Min Act: -0.1700
Data Index: 1166871 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4358. Min Act: -0.1700
Data Index: 5076055 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4670. Min Act: -0.1700
Data Index: 1432978 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4670. Min Act: -0.1700
Data Index: 4195347 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4358. Min Act: -0.1700
Data Index: 1372847 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4358. Min Act: -0.1700
Data Index: 499932 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4358. Min Act: -0.1700
Data Index: 8767755 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4358. Min Act: -0.1700
Data Index: 1582100 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4670. Min Act: -0.1700
Data Index: 2472041 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8420. Min Range: -6.8420
Max Act: 6.4045. Min Act: -0.1700
Data Index: 5563405 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19