Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5917. Min Act: -0.1700
Data Index: 1035233 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5291. Min Act: -0.1700
Data Index: 6966341 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.5134. Min Act: -0.1700
Data Index: 514713 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4977. Min Act: -0.1700
Data Index: 5724515 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4508. Min Act: -0.1700
Data Index: 514714 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4821. Min Act: -0.1700
Data Index: 1609258 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4351. Min Act: -0.1700
Data Index: 5718450 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4351. Min Act: -0.1700
Data Index: 7451685 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4351. Min Act: -0.1700
Data Index: 6449368 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4194. Min Act: -0.1700
Data Index: 7511227 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4194. Min Act: -0.1700
Data Index: 7692457 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.3881. Min Act: -0.1700
Data Index: 728923 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.4194. Min Act: -0.1700
Data Index: 3089213 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.3881. Min Act: -0.1700
Data Index: 5056616 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.3881. Min Act: -0.1700
Data Index: 5737260 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.3567. Min Act: -0.1700
Data Index: 4408972 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.3724. Min Act: -0.1700
Data Index: 5373100 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.3567. Min Act: -0.1700
Data Index: 7493172 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.3724. Min Act: -0.1700
Data Index: 4962365 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5917. Min Range: -3.5917
Max Act: 3.3410. Min Act: -0.1700
Data Index: 1597290 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19