Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4603. Min Range: -6.4603
Max Act: 6.4603. Min Act: -0.1700
Data Index: 6820253 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4603. Min Range: -6.4603
Max Act: 6.4291. Min Act: -0.1700
Data Index: 4507021 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4603. Min Range: -6.4603
Max Act: 6.2103. Min Act: -0.1700
Data Index: 797874 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4603. Min Range: -6.4603
Max Act: 6.0228. Min Act: -0.1700
Data Index: 2641398 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4603. Min Range: -6.4603
Max Act: 6.0228. Min Act: -0.1700
Data Index: 2350853 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.9603. Min Act: -0.1700
Data Index: 2869980 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.8666. Min Act: -0.1700
Data Index: 223920 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.8666. Min Act: -0.1700
Data Index: 4227719 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.8666. Min Act: -0.1700
Data Index: 6036827 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.8353. Min Act: -0.1700
Data Index: 663140 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.8041. Min Act: -0.1700
Data Index: 2818891 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.7728. Min Act: -0.1700
Data Index: 2705412 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.8041. Min Act: -0.1700
Data Index: 5391605 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.8041. Min Act: -0.1700
Data Index: 7428225 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.8041. Min Act: -0.1700
Data Index: 4685639 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.7728. Min Act: -0.1700
Data Index: 5800926 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.7728. Min Act: -0.1700
Data Index: 5976331 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.7728. Min Act: -0.1700
Data Index: 2398963 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.7728. Min Act: -0.1700
Data Index: 2606016 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4603. Min Range: -6.4603
Max Act: 5.7728. Min Act: -0.1700
Data Index: 4319571 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19