Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5152 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.9231. Min Act: -0.1700
Data Index: 5481816 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.8606. Min Act: -0.1700
Data Index: 8799670 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.8293. Min Act: -0.1700
Data Index: 3003429 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7981. Min Act: -0.1699
Data Index: 1003974 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1700
Data Index: 6795503 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1700
Data Index: 4154326 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1698
Data Index: 919107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1700
Data Index: 3481947 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1700
Data Index: 765879 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1697
Data Index: 5683153 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1700
Data Index: 7305432 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1699
Data Index: 378754 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1700
Data Index: 1449797 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7668. Min Act: -0.1700
Data Index: 6363289 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7356. Min Act: -0.1700
Data Index: 398981 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7356. Min Act: -0.1700
Data Index: 5749082 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7356. Min Act: -0.1700
Data Index: 3543896 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7043. Min Act: -0.1700
Data Index: 3922545 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7356. Min Act: -0.1700
Data Index: 2028112 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.7356. Min Act: -0.1700
Data Index: 2190107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19