Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5783 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6725. Min Act: -0.1700
Data Index: 8694248 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.6412. Min Act: -0.1700
Data Index: 2247829 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5162. Min Act: -0.1700
Data Index: 6874309 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5162. Min Act: -0.1700
Data Index: 3994063 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.5475. Min Act: -0.1700
Data Index: 8087195 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4850. Min Act: -0.1700
Data Index: 1519288 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.4537. Min Act: -0.1700
Data Index: 3007477 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3912. Min Act: -0.1700
Data Index: 809481 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3600. Min Act: -0.1700
Data Index: 4664096 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.3287. Min Act: -0.1700
Data Index: 5001748 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2662. Min Act: -0.1700
Data Index: 2552832 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2975. Min Act: -0.1700
Data Index: 6282359 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2975. Min Act: -0.1700
Data Index: 570287 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2350. Min Act: -0.1700
Data Index: 7764532 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 4593391 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2037. Min Act: -0.1700
Data Index: 5435326 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.2037. Min Act: -0.1700
Data Index: 7337302 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 5605041 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.1725. Min Act: -0.1700
Data Index: 7397264 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6725. Min Range: -5.6725
Max Act: 5.1412. Min Act: -0.1700
Data Index: 4709397 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19