Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2699. Min Range: -3.2699
Max Act: 3.2699. Min Act: -0.1700
Data Index: 4660265 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2699. Min Range: -3.2699
Max Act: 3.0811. Min Act: -0.1700
Data Index: 7377398 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2699. Min Range: -3.2699
Max Act: 3.0811. Min Act: -0.1700
Data Index: 4348581 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2699. Min Range: -3.2699
Max Act: 3.0654. Min Act: -0.1700
Data Index: 2849048 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2699. Min Range: -3.2699
Max Act: 3.0338. Min Act: -0.1700
Data Index: 4672712 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2699. Min Range: -3.2699
Max Act: 3.0180. Min Act: -0.1700
Data Index: 3767408 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9864. Min Act: -0.1700
Data Index: 7116908 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9864. Min Act: -0.1700
Data Index: 7116907 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2699. Min Range: -3.2699
Max Act: 3.0022. Min Act: -0.1700
Data Index: 4411497 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9548. Min Act: -0.1700
Data Index: 6763558 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9389. Min Act: -0.1700
Data Index: 7377397 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9548. Min Act: -0.1700
Data Index: 5998584 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9389. Min Act: -0.1700
Data Index: 4430500 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9231. Min Act: -0.1700
Data Index: 6552888 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9389. Min Act: -0.1700
Data Index: 2849047 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9231. Min Act: -0.1700
Data Index: 7567066 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9231. Min Act: -0.1700
Data Index: 4614415 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9231. Min Act: -0.1700
Data Index: 1452768 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9231. Min Act: -0.1700
Data Index: 3446642 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2699. Min Range: -3.2699
Max Act: 2.9072. Min Act: -0.1700
Data Index: 4876694 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19