Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.9481. Min Act: -0.1700
Data Index: 6076525 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.2918. Min Act: -0.1700
Data Index: 971111 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.2918. Min Act: -0.1700
Data Index: 5992395 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.2606. Min Act: -0.1700
Data Index: 5173914 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.2606. Min Act: -0.1700
Data Index: 58214 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.2293. Min Act: -0.1700
Data Index: 3370741 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.2293. Min Act: -0.1700
Data Index: 1500635 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.2293. Min Act: -0.1700
Data Index: 5619114 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.2293. Min Act: -0.1700
Data Index: 5910365 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.1668. Min Act: -0.1700
Data Index: 8399939 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.1356. Min Act: -0.1700
Data Index: 2509755 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.1356. Min Act: -0.1700
Data Index: 8597124 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.1356. Min Act: -0.1700
Data Index: 762488 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.1043. Min Act: -0.1700
Data Index: 2990721 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.0731. Min Act: -0.1700
Data Index: 2337564 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.0731. Min Act: -0.1700
Data Index: 5625335 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.0418. Min Act: -0.1700
Data Index: 5447973 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.0106. Min Act: -0.1700
Data Index: 8546802 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.0418. Min Act: -0.1700
Data Index: 5966595 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9481. Min Range: -7.9481
Max Act: 7.0106. Min Act: -0.1700
Data Index: 899903 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19