Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 361 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.8242. Min Act: -0.1700
Data Index: 4754378 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.7617. Min Act: -0.1700
Data Index: 6772023 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.6055. Min Act: -0.1700
Data Index: 4563515 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.5742. Min Act: -0.1700
Data Index: 8669732 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.5430. Min Act: -0.1700
Data Index: 4073939 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.5430. Min Act: -0.1700
Data Index: 7725385 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.6055. Min Act: -0.1700
Data Index: 8160885 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.5117. Min Act: -0.1700
Data Index: 5466990 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.5117. Min Act: -0.1700
Data Index: 7190316 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.5430. Min Act: -0.1700
Data Index: 768597 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.4492. Min Act: -0.1700
Data Index: 452587 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.5117. Min Act: -0.1700
Data Index: 3296109 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.4805. Min Act: -0.1700
Data Index: 8306769 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.4492. Min Act: -0.1700
Data Index: 7925651 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.4492. Min Act: -0.1700
Data Index: 4151876 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.4805. Min Act: -0.1700
Data Index: 7481247 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.4492. Min Act: -0.1700
Data Index: 186341 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.4180. Min Act: -0.1700
Data Index: 6789492 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.3867. Min Act: -0.1700
Data Index: 1530998 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8242. Min Range: -5.8242
Max Act: 5.3867. Min Act: -0.1700
Data Index: 1383805 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19