Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4492 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0927. Min Range: -5.0927
Max Act: 5.0927. Min Act: -0.1700
Data Index: 1323685 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.7802. Min Act: -0.1700
Data Index: 4643423 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.7802. Min Act: -0.1700
Data Index: 5386250 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.7489. Min Act: -0.1700
Data Index: 8588534 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.7177. Min Act: -0.1700
Data Index: 6202689 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.6864. Min Act: -0.1700
Data Index: 8667929 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.6552. Min Act: -0.1700
Data Index: 7885618 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.6239. Min Act: -0.1700
Data Index: 5654365 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5927. Min Act: -0.1700
Data Index: 4280900 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5927. Min Act: -0.1700
Data Index: 937497 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5614. Min Act: -0.1700
Data Index: 440498 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5927. Min Act: -0.1700
Data Index: 6921858 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5614. Min Act: -0.1700
Data Index: 6421906 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5614. Min Act: -0.1700
Data Index: 5414264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 5306190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 3536018 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 5792030 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5614. Min Act: -0.1700
Data Index: 8524020 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5614. Min Act: -0.1700
Data Index: 8480263 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0927. Min Range: -5.0927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 7143190 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19