Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2326 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.2439. Min Act: -0.1700
Data Index: 7468563 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.2125. Min Act: -0.1700
Data Index: 7550581 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1967. Min Act: -0.1700
Data Index: 2240403 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1967. Min Act: -0.1700
Data Index: 4574762 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.2125. Min Act: -0.1700
Data Index: 3979610 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1180. Min Act: -0.1700
Data Index: 925086 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1338. Min Act: -0.1700
Data Index: 5125038 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1180. Min Act: -0.1700
Data Index: 1490684 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1180. Min Act: -0.1700
Data Index: 1111212 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1338. Min Act: -0.1700
Data Index: 602050 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1180. Min Act: -0.1700
Data Index: 2906396 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1180. Min Act: -0.1700
Data Index: 6421285 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.0865. Min Act: -0.1700
Data Index: 6859566 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.0865. Min Act: -0.1700
Data Index: 5209804 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1023. Min Act: -0.1700
Data Index: 5436563 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1180. Min Act: -0.1700
Data Index: 4629178 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.0865. Min Act: -0.1700
Data Index: 4149840 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1023. Min Act: -0.1700
Data Index: 1033255 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.1023. Min Act: -0.1700
Data Index: 2894855 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2439. Min Range: -3.2439
Max Act: 3.0707. Min Act: -0.1700
Data Index: 4172429 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19