Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2619 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.4069. Min Act: -0.1700
Data Index: 3698066 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.4069. Min Act: -0.1700
Data Index: 2490716 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.2194. Min Act: -0.1700
Data Index: 4613393 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.2507. Min Act: -0.1700
Data Index: 3960327 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.1882. Min Act: -0.1700
Data Index: 4863086 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.1882. Min Act: -0.1700
Data Index: 3642369 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.1257. Min Act: -0.1700
Data Index: 5841339 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0944. Min Act: -0.1700
Data Index: 7745898 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0632. Min Act: -0.1700
Data Index: 2729340 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0632. Min Act: -0.1700
Data Index: 5322355 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0319. Min Act: -0.1700
Data Index: 7863726 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0319. Min Act: -0.1700
Data Index: 3590699 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0319. Min Act: -0.1700
Data Index: 1193362 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0319. Min Act: -0.1700
Data Index: 3609536 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0319. Min Act: -0.1700
Data Index: 3895953 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0632. Min Act: -0.1700
Data Index: 6765081 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0007. Min Act: -0.1700
Data Index: 1466062 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0007. Min Act: -0.1700
Data Index: 4793336 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4069. Min Range: -6.4069
Max Act: 6.0007. Min Act: -0.1700
Data Index: 7735198 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4069. Min Range: -6.4069
Max Act: 5.9694. Min Act: -0.1700
Data Index: 6883129 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19