Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.7438. Min Act: -0.1700
Data Index: 3197889 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.6501. Min Act: -0.1700
Data Index: 2023080 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.6501. Min Act: -0.1700
Data Index: 8270226 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.5563. Min Act: -0.1700
Data Index: 4728610 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.5563. Min Act: -0.1700
Data Index: 8270230 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.5563. Min Act: -0.1700
Data Index: 8602224 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.4313. Min Act: -0.1700
Data Index: 2273818 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.4313. Min Act: -0.1700
Data Index: 8270224 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.4626. Min Act: -0.1700
Data Index: 3197888 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.4313. Min Act: -0.1700
Data Index: 6898558 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.4001. Min Act: -0.1700
Data Index: 4477742 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.4001. Min Act: -0.1700
Data Index: 7332229 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.3376. Min Act: -0.1700
Data Index: 1276647 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.3688. Min Act: -0.1700
Data Index: 1088112 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.3063. Min Act: -0.1700
Data Index: 1587766 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.3063. Min Act: -0.1700
Data Index: 8270229 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.3688. Min Act: -0.1700
Data Index: 4302248 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.3688. Min Act: -0.1700
Data Index: 1933319 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.3063. Min Act: -0.1700
Data Index: 1484051 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7438. Min Range: -6.7438
Max Act: 6.3376. Min Act: -0.1700
Data Index: 7332230 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19