Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4215 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3312. Min Range: -9.3312
Max Act: 9.3312. Min Act: -0.1700
Data Index: 7674399 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3312. Min Range: -9.3312
Max Act: 9.2687. Min Act: -0.1700
Data Index: 4566967 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3312. Min Range: -9.3312
Max Act: 9.1437. Min Act: -0.1700
Data Index: 2495254 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3312. Min Range: -9.3312
Max Act: 9.0812. Min Act: -0.1700
Data Index: 3919627 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3312. Min Range: -9.3312
Max Act: 9.0812. Min Act: -0.1700
Data Index: 4540501 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3312. Min Range: -9.3312
Max Act: 9.0187. Min Act: -0.1700
Data Index: 6775307 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3312. Min Range: -9.3312
Max Act: 9.0187. Min Act: -0.1700
Data Index: 5088433 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.8937. Min Act: -0.1700
Data Index: 337318 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.8937. Min Act: -0.1700
Data Index: 5374869 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.8312. Min Act: -0.1700
Data Index: 7590776 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.8312. Min Act: -0.1700
Data Index: 1085506 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.8312. Min Act: -0.1700
Data Index: 461255 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.8312. Min Act: -0.1700
Data Index: 8379662 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.7687. Min Act: -0.1700
Data Index: 3421934 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.7687. Min Act: -0.1700
Data Index: 3876801 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.7687. Min Act: -0.1700
Data Index: 4309985 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.6437. Min Act: -0.1700
Data Index: 8234494 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.7062. Min Act: -0.1700
Data Index: 3152887 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.7687. Min Act: -0.1700
Data Index: 4421572 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3312. Min Range: -9.3312
Max Act: 8.7062. Min Act: -0.1700
Data Index: 2067057 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19