Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7601. Min Act: -0.1700
Data Index: 317000 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7342. Min Act: -0.1700
Data Index: 4175371 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7342. Min Act: -0.1700
Data Index: 3067476 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6995. Min Act: -0.1700
Data Index: 8323633 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7428. Min Act: -0.1700
Data Index: 5574893 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7169. Min Act: -0.1700
Data Index: 1748867 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7255. Min Act: -0.1699
Data Index: 2244547 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7342. Min Act: -0.1700
Data Index: 3374767 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7169. Min Act: -0.1700
Data Index: 8513867 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7082. Min Act: -0.1700
Data Index: 5786723 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.7082. Min Act: -0.1700
Data Index: 6684459 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6995. Min Act: -0.1700
Data Index: 6098144 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6822. Min Act: -0.1700
Data Index: 1769060 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6909. Min Act: -0.1700
Data Index: 2653367 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6822. Min Act: -0.1700
Data Index: 2592173 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6822. Min Act: -0.1700
Data Index: 537693 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6822. Min Act: -0.1700
Data Index: 2262738 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6648. Min Act: -0.1700
Data Index: 320719 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6561. Min Act: -0.1700
Data Index: 614740 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7601. Min Range: -1.7601
Max Act: 1.6648. Min Act: -0.1700
Data Index: 4230509 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19