Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.5374. Min Act: -0.1700
Data Index: 5868079 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.2874. Min Act: -0.1700
Data Index: 6782787 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.1624. Min Act: -0.1700
Data Index: 4163318 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.1312. Min Act: -0.1700
Data Index: 2645954 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.1312. Min Act: -0.1700
Data Index: 6604102 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.1312. Min Act: -0.1700
Data Index: 2527995 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.0062. Min Act: -0.1700
Data Index: 6687434 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.0062. Min Act: -0.1700
Data Index: 3750534 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.0062. Min Act: -0.1700
Data Index: 921497 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5374. Min Range: -7.5374
Max Act: 7.0062. Min Act: -0.1700
Data Index: 323323 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.9749. Min Act: -0.1700
Data Index: 2736922 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.9437. Min Act: -0.1700
Data Index: 985834 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.9437. Min Act: -0.1700
Data Index: 8694868 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.8812. Min Act: -0.1700
Data Index: 8805716 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.9124. Min Act: -0.1700
Data Index: 5453635 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.9124. Min Act: -0.1700
Data Index: 8522656 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.9124. Min Act: -0.1700
Data Index: 1187110 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.9437. Min Act: -0.1700
Data Index: 268747 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.9124. Min Act: -0.1700
Data Index: 3098820 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5374. Min Range: -7.5374
Max Act: 6.8499. Min Act: -0.1700
Data Index: 2417691 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19