Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7432. Min Range: -6.7432
Max Act: 6.7432. Min Act: -0.1700
Data Index: 6182082 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7432. Min Range: -6.7432
Max Act: 6.5244. Min Act: -0.1700
Data Index: 7483026 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7432. Min Range: -6.7432
Max Act: 6.0869. Min Act: -0.1700
Data Index: 6351105 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7432. Min Range: -6.7432
Max Act: 6.0557. Min Act: -0.1700
Data Index: 6355622 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.9932. Min Act: -0.1700
Data Index: 506308 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.9307. Min Act: -0.1700
Data Index: 2200076 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.9307. Min Act: -0.1700
Data Index: 6637598 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.8994. Min Act: -0.1700
Data Index: 8634167 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.8369. Min Act: -0.1700
Data Index: 3348560 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.8057. Min Act: -0.1700
Data Index: 5098007 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.8057. Min Act: -0.1700
Data Index: 1483703 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.8057. Min Act: -0.1700
Data Index: 1870324 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.8057. Min Act: -0.1700
Data Index: 6240607 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.7744. Min Act: -0.1700
Data Index: 4369530 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.7744. Min Act: -0.1700
Data Index: 944761 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.7432. Min Act: -0.1700
Data Index: 2733617 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.7744. Min Act: -0.1700
Data Index: 6307292 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.7432. Min Act: -0.1700
Data Index: 5704341 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.7432. Min Act: -0.1700
Data Index: 3574323 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7432. Min Range: -6.7432
Max Act: 5.7119. Min Act: -0.1700
Data Index: 696740 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19