Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1618 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1868. Min Range: -4.1868
Max Act: 4.1868. Min Act: -0.1700
Data Index: 6826005 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1868. Min Range: -4.1868
Max Act: 4.1243. Min Act: -0.1700
Data Index: 6826008 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1868. Min Range: -4.1868
Max Act: 4.0618. Min Act: -0.1700
Data Index: 3273370 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1868. Min Range: -4.1868
Max Act: 4.0306. Min Act: -0.1700
Data Index: 5795108 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.9993. Min Act: -0.1700
Data Index: 7921695 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.9680. Min Act: -0.1700
Data Index: 3818188 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.9368. Min Act: -0.1700
Data Index: 6026684 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.9368. Min Act: -0.1700
Data Index: 8571937 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.8742. Min Act: -0.1700
Data Index: 6456388 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.8742. Min Act: -0.1700
Data Index: 121879 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.8742. Min Act: -0.1700
Data Index: 5965843 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.8742. Min Act: -0.1700
Data Index: 7706312 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.8430. Min Act: -0.1700
Data Index: 3362405 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.8430. Min Act: -0.1700
Data Index: 6900526 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.8117. Min Act: -0.1700
Data Index: 7126105 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.7804. Min Act: -0.1700
Data Index: 313568 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.7804. Min Act: -0.1700
Data Index: 8349858 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.7492. Min Act: -0.1700
Data Index: 7921690 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.7648. Min Act: -0.1700
Data Index: 6191537 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1868. Min Range: -4.1868
Max Act: 3.7492. Min Act: -0.1700
Data Index: 7564469 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19