Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4523. Min Range: -8.4523
Max Act: 8.4523. Min Act: -0.1700
Data Index: 5344444 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4523. Min Range: -8.4523
Max Act: 8.0773. Min Act: -0.1700
Data Index: 7967466 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4523. Min Range: -8.4523
Max Act: 8.0148. Min Act: -0.1700
Data Index: 8506927 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4523. Min Range: -8.4523
Max Act: 8.0148. Min Act: -0.1700
Data Index: 742918 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.8898. Min Act: -0.1700
Data Index: 1264593 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.8898. Min Act: -0.1700
Data Index: 8757860 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.8898. Min Act: -0.1700
Data Index: 1624499 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7648. Min Act: -0.1700
Data Index: 2627547 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.8273. Min Act: -0.1700
Data Index: 3714701 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.8273. Min Act: -0.1700
Data Index: 1118076 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7648. Min Act: -0.1700
Data Index: 731218 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7648. Min Act: -0.1700
Data Index: 4921548 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7335. Min Act: -0.1700
Data Index: 3320079 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7648. Min Act: -0.1700
Data Index: 2498860 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7335. Min Act: -0.1700
Data Index: 1719704 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7335. Min Act: -0.1700
Data Index: 7699856 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7023. Min Act: -0.1700
Data Index: 6597272 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.7023. Min Act: -0.1700
Data Index: 1644916 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.6710. Min Act: -0.1700
Data Index: 344563 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4523. Min Range: -8.4523
Max Act: 7.6398. Min Act: -0.1700
Data Index: 187339 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19