Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.9665. Min Act: -0.1700
Data Index: 6793907 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.9040. Min Act: -0.1700
Data Index: 6448925 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.6852. Min Act: -0.1700
Data Index: 482150 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.6227. Min Act: -0.1700
Data Index: 3024694 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.6227. Min Act: -0.1700
Data Index: 4410072 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.6227. Min Act: -0.1700
Data Index: 5000719 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.5602. Min Act: -0.1700
Data Index: 4364041 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4977. Min Act: -0.1700
Data Index: 8130765 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4665. Min Act: -0.1700
Data Index: 7203165 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4977. Min Act: -0.1700
Data Index: 4911128 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4665. Min Act: -0.1700
Data Index: 8337051 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4352. Min Act: -0.1700
Data Index: 4883928 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4352. Min Act: -0.1700
Data Index: 1525795 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4352. Min Act: -0.1700
Data Index: 3343316 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4040. Min Act: -0.1700
Data Index: 1218273 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.4040. Min Act: -0.1700
Data Index: 5269027 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.3727. Min Act: -0.1700
Data Index: 819299 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.3727. Min Act: -0.1700
Data Index: 3757721 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.3727. Min Act: -0.1700
Data Index: 4689164 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9665. Min Range: -7.9665
Max Act: 7.3415. Min Act: -0.1700
Data Index: 6331340 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19