Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 671 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.5102. Min Act: -0.1700
Data Index: 8803079 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.4477. Min Act: -0.1700
Data Index: 6044634 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.4477. Min Act: -0.1700
Data Index: 8255927 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.4164. Min Act: -0.1700
Data Index: 5872185 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.4164. Min Act: -0.1700
Data Index: 6559068 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.4477. Min Act: -0.1700
Data Index: 2499517 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.4164. Min Act: -0.1700
Data Index: 5373508 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.3852. Min Act: -0.1700
Data Index: 40211 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.3852. Min Act: -0.1700
Data Index: 6373589 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.3852. Min Act: -0.1700
Data Index: 4025865 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.3227. Min Act: -0.1700
Data Index: 63835 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.3227. Min Act: -0.1700
Data Index: 4066744 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.3227. Min Act: -0.1700
Data Index: 7536947 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.2914. Min Act: -0.1700
Data Index: 3497457 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.2914. Min Act: -0.1700
Data Index: 4546556 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.2914. Min Act: -0.1700
Data Index: 5856998 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.2289. Min Act: -0.1700
Data Index: 6296574 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.2602. Min Act: -0.1700
Data Index: 6497205 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.2914. Min Act: -0.1700
Data Index: 5582995 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5102. Min Range: -5.5102
Max Act: 5.2602. Min Act: -0.1700
Data Index: 7402134 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19