Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1808 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0204. Min Range: -6.0204
Max Act: 6.0204. Min Act: -0.1700
Data Index: 8405588 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.9891. Min Act: -0.1700
Data Index: 637643 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.9266. Min Act: -0.1700
Data Index: 1439585 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.9266. Min Act: -0.1694
Data Index: 2859895 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.9266. Min Act: -0.1700
Data Index: 3300846 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8954. Min Act: -0.1699
Data Index: 5229573 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8329. Min Act: -0.1700
Data Index: 1871491 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8329. Min Act: -0.1700
Data Index: 3669303 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8016. Min Act: -0.1700
Data Index: 8527681 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8329. Min Act: -0.1700
Data Index: 7213003 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8329. Min Act: -0.1700
Data Index: 5261227 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7391. Min Act: -0.1700
Data Index: 3169910 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8016. Min Act: -0.1700
Data Index: 8053662 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7704. Min Act: -0.1700
Data Index: 2604881 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7391. Min Act: -0.1700
Data Index: 5715015 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7704. Min Act: -0.1700
Data Index: 8667797 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7079. Min Act: -0.1700
Data Index: 1760900 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7079. Min Act: -0.1700
Data Index: 7297295 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7079. Min Act: -0.1700
Data Index: 7727411 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6766. Min Act: -0.1700
Data Index: 3412250 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19