Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1901 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0346. Min Range: -6.0346
Max Act: 6.0346. Min Act: -0.1700
Data Index: 6929321 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.9096. Min Act: -0.1700
Data Index: 5494628 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.7533. Min Act: -0.1700
Data Index: 586760 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.6908. Min Act: -0.1700
Data Index: 480562 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.6596. Min Act: -0.1700
Data Index: 5072889 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.6596. Min Act: -0.1700
Data Index: 6360061 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.6283. Min Act: -0.1700
Data Index: 4641456 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.6283. Min Act: -0.1700
Data Index: 2301254 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5971. Min Act: -0.1700
Data Index: 8160928 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.6283. Min Act: -0.1700
Data Index: 820778 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5658. Min Act: -0.1700
Data Index: 4644482 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5971. Min Act: -0.1700
Data Index: 1080776 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3927093 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5971. Min Act: -0.1700
Data Index: 564401 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5971. Min Act: -0.1700
Data Index: 5394533 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5346. Min Act: -0.1700
Data Index: 4190641 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5658. Min Act: -0.1700
Data Index: 6612239 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5033. Min Act: -0.1700
Data Index: 2143761 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5033. Min Act: -0.1700
Data Index: 7614470 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0346. Min Range: -6.0346
Max Act: 5.5033. Min Act: -0.1700
Data Index: 2201813 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19