Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0332. Min Range: -5.0332
Max Act: 5.0332. Min Act: -0.1700
Data Index: 1621354 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8770. Min Act: -0.1700
Data Index: 5128799 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8457. Min Act: -0.1700
Data Index: 383 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8770. Min Act: -0.1700
Data Index: 298791 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8145. Min Act: -0.1700
Data Index: 353649 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8145. Min Act: -0.1700
Data Index: 3379327 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8457. Min Act: -0.1700
Data Index: 6018385 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8457. Min Act: -0.1700
Data Index: 3702492 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7832. Min Act: -0.1700
Data Index: 5159754 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7832. Min Act: -0.1700
Data Index: 6370488 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7832. Min Act: -0.1700
Data Index: 2552807 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7520. Min Act: -0.1700
Data Index: 435366 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7520. Min Act: -0.1700
Data Index: 1726573 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7207. Min Act: -0.1700
Data Index: 6134513 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7520. Min Act: -0.1700
Data Index: 1693647 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7520. Min Act: -0.1700
Data Index: 3374823 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7520. Min Act: -0.1700
Data Index: 5930481 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7520. Min Act: -0.1700
Data Index: 5204209 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7520. Min Act: -0.1700
Data Index: 4828334 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7520. Min Act: -0.1700
Data Index: 1746359 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19