Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.9881. Min Act: -0.1700
Data Index: 6245908 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.8006. Min Act: -0.1700
Data Index: 3290216 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.4881. Min Act: -0.1700
Data Index: 1032999 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.4881. Min Act: -0.1700
Data Index: 1665158 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.3631. Min Act: -0.1700
Data Index: 4911326 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.3319. Min Act: -0.1700
Data Index: 5470808 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.3006. Min Act: -0.1700
Data Index: 1740118 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.2694. Min Act: -0.1700
Data Index: 6488124 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.2694. Min Act: -0.1700
Data Index: 4965140 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.2694. Min Act: -0.1700
Data Index: 6536306 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.2694. Min Act: -0.1700
Data Index: 2493847 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.2069. Min Act: -0.1700
Data Index: 6172383 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.2381. Min Act: -0.1700
Data Index: 2609947 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.1756. Min Act: -0.1700
Data Index: 5529954 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.1756. Min Act: -0.1700
Data Index: 2682927 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.1444. Min Act: -0.1700
Data Index: 3359967 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.1444. Min Act: -0.1700
Data Index: 8223109 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.1444. Min Act: -0.1700
Data Index: 3196583 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.1131. Min Act: -0.1700
Data Index: 6488122 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9881. Min Range: -6.9881
Max Act: 6.1444. Min Act: -0.1700
Data Index: 2207090 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19