Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0140. Min Range: -6.0140
Max Act: 6.0140. Min Act: -0.1700
Data Index: 5752093 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.8578. Min Act: -0.1700
Data Index: 7267939 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.8265. Min Act: -0.1700
Data Index: 6753651 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.7953. Min Act: -0.1700
Data Index: 5842053 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.7953. Min Act: -0.1700
Data Index: 5291959 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.7640. Min Act: -0.1700
Data Index: 1263119 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.7328. Min Act: -0.1700
Data Index: 4095517 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.7328. Min Act: -0.1700
Data Index: 828054 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.6703. Min Act: -0.1700
Data Index: 990869 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.6703. Min Act: -0.1700
Data Index: 6502487 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.6703. Min Act: -0.1700
Data Index: 1737904 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.7015. Min Act: -0.1700
Data Index: 3613406 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.6390. Min Act: -0.1700
Data Index: 6054223 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.6390. Min Act: -0.1700
Data Index: 516995 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.6390. Min Act: -0.1700
Data Index: 450328 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.6078. Min Act: -0.1700
Data Index: 6700487 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.6078. Min Act: -0.1700
Data Index: 8526566 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.5765. Min Act: -0.1700
Data Index: 4060583 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.5765. Min Act: -0.1700
Data Index: 946362 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0140. Min Range: -6.0140
Max Act: 5.5765. Min Act: -0.1700
Data Index: 5445004 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19