Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1777 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.6226. Min Act: -0.1700
Data Index: 327629 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.5289. Min Act: -0.1700
Data Index: 7958557 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.5289. Min Act: -0.1700
Data Index: 8710188 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.4351. Min Act: -0.1700
Data Index: 6176383 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.4039. Min Act: -0.1700
Data Index: 7601237 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.3101. Min Act: -0.1700
Data Index: 4440859 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.3414. Min Act: -0.1700
Data Index: 7439645 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.3101. Min Act: -0.1700
Data Index: 6622318 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.3414. Min Act: -0.1700
Data Index: 1209105 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.2789. Min Act: -0.1700
Data Index: 2926722 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.2789. Min Act: -0.1700
Data Index: 2840460 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.2476. Min Act: -0.1700
Data Index: 2612959 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.2476. Min Act: -0.1700
Data Index: 2242607 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.2789. Min Act: -0.1700
Data Index: 4326297 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.2164. Min Act: -0.1700
Data Index: 375855 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.2164. Min Act: -0.1700
Data Index: 2433630 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.2476. Min Act: -0.1700
Data Index: 1732318 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.1539. Min Act: -0.1700
Data Index: 4304739 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.1851. Min Act: -0.1700
Data Index: 1829087 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6226. Min Range: -7.6226
Max Act: 7.1539. Min Act: -0.1700
Data Index: 7929262 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19