Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4081 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.7288. Min Act: -0.1700
Data Index: 7973754 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.5100. Min Act: -0.1700
Data Index: 924296 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.4788. Min Act: -0.1700
Data Index: 5599035 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.4788. Min Act: -0.1700
Data Index: 4067375 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.4475. Min Act: -0.1700
Data Index: 7074773 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.4163. Min Act: -0.1700
Data Index: 4953496 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.4475. Min Act: -0.1700
Data Index: 6079311 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3850. Min Act: -0.1700
Data Index: 2592495 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.4163. Min Act: -0.1700
Data Index: 5136546 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.4163. Min Act: -0.1700
Data Index: 8198831 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3538. Min Act: -0.1700
Data Index: 7578795 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3538. Min Act: -0.1700
Data Index: 191846 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3538. Min Act: -0.1700
Data Index: 7375637 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3538. Min Act: -0.1700
Data Index: 7375470 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3225. Min Act: -0.1700
Data Index: 3643155 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3225. Min Act: -0.1700
Data Index: 69163 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3225. Min Act: -0.1700
Data Index: 4701305 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3225. Min Act: -0.1700
Data Index: 3123637 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3225. Min Act: -0.1700
Data Index: 2031041 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7288. Min Range: -4.7288
Max Act: 4.3225. Min Act: -0.1700
Data Index: 4347349 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19