Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 744 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.5198. Min Act: -0.1700
Data Index: 2882667 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.3948. Min Act: -0.1700
Data Index: 2277716 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.4573. Min Act: -0.1700
Data Index: 547093 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.3323. Min Act: -0.1700
Data Index: 8167032 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.2698. Min Act: -0.1700
Data Index: 4577628 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.2073. Min Act: -0.1700
Data Index: 3064171 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.1448. Min Act: -0.1700
Data Index: 5209520 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.1448. Min Act: -0.1700
Data Index: 2109573 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.0823. Min Act: -0.1700
Data Index: 1600895 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.0198. Min Act: -0.1699
Data Index: 1467437 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5198. Min Range: -10.5198
Max Act: 10.0198. Min Act: -0.1700
Data Index: 4154884 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.8948. Min Act: -0.1700
Data Index: 6368605 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.9573. Min Act: -0.1700
Data Index: 8500700 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.9573. Min Act: -0.1700
Data Index: 3040531 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.8948. Min Act: -0.1700
Data Index: 8668 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.8948. Min Act: -0.1700
Data Index: 1640708 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.8323. Min Act: -0.1700
Data Index: 6082394 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.8323. Min Act: -0.1700
Data Index: 5787991 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.8323. Min Act: -0.1700
Data Index: 6242689 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5198. Min Range: -10.5198
Max Act: 9.8323. Min Act: -0.1700
Data Index: 757185 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19