Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 652 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.6888. Min Act: -0.1700
Data Index: 3522254 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.6888. Min Act: -0.1700
Data Index: 4667371 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.6575. Min Act: -0.1700
Data Index: 8565542 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5950. Min Act: -0.1700
Data Index: 2862529 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5950. Min Act: -0.1700
Data Index: 4648014 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5950. Min Act: -0.1700
Data Index: 5925193 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5638. Min Act: -0.1700
Data Index: 1822478 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.6263. Min Act: -0.1700
Data Index: 4107072 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5950. Min Act: -0.1700
Data Index: 7724158 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5638. Min Act: -0.1700
Data Index: 1734561 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5950. Min Act: -0.1700
Data Index: 497409 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5638. Min Act: -0.1700
Data Index: 2060863 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5325. Min Act: -0.1700
Data Index: 7931894 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5638. Min Act: -0.1700
Data Index: 8287219 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5325. Min Act: -0.1700
Data Index: 2923294 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5325. Min Act: -0.1700
Data Index: 8283237 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5013. Min Act: -0.1700
Data Index: 7463746 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.4700. Min Act: -0.1700
Data Index: 7541225 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5325. Min Act: -0.1700
Data Index: 6140643 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6888. Min Range: -5.6888
Max Act: 5.5013. Min Act: -0.1700
Data Index: 3398169 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19