Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2556 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2856. Min Range: -5.2856
Max Act: 5.2856. Min Act: -0.1700
Data Index: 2012164 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2856. Min Range: -5.2856
Max Act: 5.0356. Min Act: -0.1700
Data Index: 5728885 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2856. Min Range: -5.2856
Max Act: 5.0356. Min Act: -0.1700
Data Index: 1582479 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.9419. Min Act: -0.1700
Data Index: 8361697 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.9419. Min Act: -0.1700
Data Index: 4991846 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.9106. Min Act: -0.1700
Data Index: 7896601 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.8794. Min Act: -0.1700
Data Index: 6873780 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.8794. Min Act: -0.1700
Data Index: 2333502 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.8794. Min Act: -0.1700
Data Index: 598662 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.8481. Min Act: -0.1700
Data Index: 7275886 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.8481. Min Act: -0.1700
Data Index: 2206531 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.8169. Min Act: -0.1700
Data Index: 1221533 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.7856. Min Act: -0.1700
Data Index: 3644740 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.8169. Min Act: -0.1700
Data Index: 8693233 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.8169. Min Act: -0.1700
Data Index: 7631063 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.7856. Min Act: -0.1700
Data Index: 7891253 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.7231. Min Act: -0.1700
Data Index: 7030865 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.7231. Min Act: -0.1700
Data Index: 5028162 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.7231. Min Act: -0.1700
Data Index: 5755545 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2856. Min Range: -5.2856
Max Act: 4.6919. Min Act: -0.1700
Data Index: 1254508 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19