Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.6477. Min Act: -0.1700
Data Index: 6837052 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.5852. Min Act: -0.1700
Data Index: 2926977 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.4915. Min Act: -0.1700
Data Index: 7783432 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.4915. Min Act: -0.1700
Data Index: 5001750 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.3977. Min Act: -0.1700
Data Index: 373485 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.3665. Min Act: -0.1700
Data Index: 2679804 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.3039. Min Act: -0.1700
Data Index: 2656977 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2727. Min Act: -0.1700
Data Index: 3093064 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2414. Min Act: -0.1700
Data Index: 5961810 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2414. Min Act: -0.1700
Data Index: 4891751 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2414. Min Act: -0.1700
Data Index: 6080556 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2727. Min Act: -0.1700
Data Index: 3546533 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2414. Min Act: -0.1700
Data Index: 6449304 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2414. Min Act: -0.1700
Data Index: 2116685 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2102. Min Act: -0.1700
Data Index: 3235664 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2102. Min Act: -0.1700
Data Index: 1227414 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.1789. Min Act: -0.1700
Data Index: 3435331 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2102. Min Act: -0.1700
Data Index: 2834018 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2102. Min Act: -0.1700
Data Index: 3099377 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6477. Min Range: -4.6477
Max Act: 4.2102. Min Act: -0.1700
Data Index: 7042623 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19