Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1210. Min Range: -9.1210
Max Act: 9.1210. Min Act: -0.1700
Data Index: 1726579 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.9335. Min Act: -0.1700
Data Index: 254615 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.8710. Min Act: -0.1700
Data Index: 492666 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.8710. Min Act: -0.1700
Data Index: 7250843 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.8085. Min Act: -0.1700
Data Index: 4225407 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.8085. Min Act: -0.1700
Data Index: 7334294 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.6835. Min Act: -0.1700
Data Index: 2261108 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.6835. Min Act: -0.1700
Data Index: 8292484 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.6835. Min Act: -0.1700
Data Index: 7164598 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.6835. Min Act: -0.1700
Data Index: 5460545 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.6210. Min Act: -0.1700
Data Index: 2281069 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.6210. Min Act: -0.1700
Data Index: 5942854 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.6210. Min Act: -0.1700
Data Index: 8547296 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.6210. Min Act: -0.1700
Data Index: 4392709 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.5585. Min Act: -0.1700
Data Index: 3367656 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.5585. Min Act: -0.1700
Data Index: 938608 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.5585. Min Act: -0.1700
Data Index: 3349301 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.5585. Min Act: -0.1700
Data Index: 208368 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.5585. Min Act: -0.1700
Data Index: 6707643 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1210. Min Range: -9.1210
Max Act: 8.4335. Min Act: -0.1700
Data Index: 1901586 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19