Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 956 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0415. Min Range: -6.0415
Max Act: 6.0415. Min Act: -0.1700
Data Index: 4669134 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.9790. Min Act: -0.1700
Data Index: 7769273 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.9477. Min Act: -0.1700
Data Index: 1672970 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.7915. Min Act: -0.1700
Data Index: 4553976 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.7915. Min Act: -0.1700
Data Index: 564309 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.7602. Min Act: -0.1700
Data Index: 530997 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6665. Min Act: -0.1700
Data Index: 8820307 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.7290. Min Act: -0.1700
Data Index: 1560272 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6977. Min Act: -0.1700
Data Index: 6660126 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6352. Min Act: -0.1700
Data Index: 5061204 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6352. Min Act: -0.1700
Data Index: 449752 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6665. Min Act: -0.1700
Data Index: 5470606 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6040. Min Act: -0.1700
Data Index: 6484961 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6040. Min Act: -0.1700
Data Index: 1845193 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6040. Min Act: -0.1700
Data Index: 5965504 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6040. Min Act: -0.1700
Data Index: 5540050 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.6040. Min Act: -0.1700
Data Index: 368156 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.5415. Min Act: -0.1700
Data Index: 2297214 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.5727. Min Act: -0.1700
Data Index: 6628774 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0415. Min Range: -6.0415
Max Act: 5.5727. Min Act: -0.1700
Data Index: 4043207 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19