Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1868. Min Range: -6.1868
Max Act: 6.1868. Min Act: -0.1700
Data Index: 656909 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1868. Min Range: -6.1868
Max Act: 6.1868. Min Act: -0.1700
Data Index: 8031795 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1868. Min Range: -6.1868
Max Act: 6.1243. Min Act: -0.1700
Data Index: 6257128 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1868. Min Range: -6.1868
Max Act: 6.0306. Min Act: -0.1700
Data Index: 3571019 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.9993. Min Act: -0.1700
Data Index: 5332728 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.9681. Min Act: -0.1700
Data Index: 8109918 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.9681. Min Act: -0.1700
Data Index: 7060608 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.9056. Min Act: -0.1700
Data Index: 871865 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.8743. Min Act: -0.1700
Data Index: 8639618 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.8431. Min Act: -0.1700
Data Index: 927113 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.8743. Min Act: -0.1700
Data Index: 4695414 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.8431. Min Act: -0.1700
Data Index: 878045 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.8431. Min Act: -0.1700
Data Index: 645979 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.8118. Min Act: -0.1700
Data Index: 1241352 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.7806. Min Act: -0.1700
Data Index: 871864 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.7493. Min Act: -0.1700
Data Index: 5917131 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.7493. Min Act: -0.1700
Data Index: 32941 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.7493. Min Act: -0.1700
Data Index: 3674725 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.7806. Min Act: -0.1700
Data Index: 654588 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1868. Min Range: -6.1868
Max Act: 5.7493. Min Act: -0.1700
Data Index: 2753978 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19