Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7499. Min Range: -7.7499
Max Act: 7.7499. Min Act: -0.1700
Data Index: 7215428 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7499. Min Range: -7.7499
Max Act: 7.2812. Min Act: -0.1700
Data Index: 3731481 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7499. Min Range: -7.7499
Max Act: 7.1874. Min Act: -0.1700
Data Index: 1083716 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7499. Min Range: -7.7499
Max Act: 7.1249. Min Act: -0.1700
Data Index: 7227037 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7499. Min Range: -7.7499
Max Act: 7.0312. Min Act: -0.1700
Data Index: 1538329 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.9999. Min Act: -0.1700
Data Index: 7818395 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7499. Min Range: -7.7499
Max Act: 7.0312. Min Act: -0.1700
Data Index: 2744740 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.9687. Min Act: -0.1700
Data Index: 4918625 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.9374. Min Act: -0.1700
Data Index: 126824 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.9374. Min Act: -0.1700
Data Index: 4926762 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.9374. Min Act: -0.1700
Data Index: 2634719 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.9374. Min Act: -0.1700
Data Index: 2737569 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.9062. Min Act: -0.1700
Data Index: 2797292 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.8749. Min Act: -0.1700
Data Index: 7466844 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.8749. Min Act: -0.1700
Data Index: 8637307 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.8749. Min Act: -0.1700
Data Index: 3949873 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.8749. Min Act: -0.1700
Data Index: 2204155 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.8749. Min Act: -0.1700
Data Index: 3131771 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.8124. Min Act: -0.1700
Data Index: 1308865 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7499. Min Range: -7.7499
Max Act: 6.7812. Min Act: -0.1700
Data Index: 1846300 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19