Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1631 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.6352. Min Act: -0.1694
Data Index: 7492958 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.6352. Min Act: -0.1700
Data Index: 8374986 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5654. Min Act: -0.1699
Data Index: 1137772 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5479. Min Act: -0.1700
Data Index: 6697483 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5654. Min Act: -0.1700
Data Index: 6096156 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5479. Min Act: -0.1696
Data Index: 3675233 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5303. Min Act: -0.1698
Data Index: 3119546 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5303. Min Act: -0.1700
Data Index: 3148296 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5479. Min Act: -0.1699
Data Index: 8243257 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5479. Min Act: -0.1692
Data Index: 3388599 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5303. Min Act: -0.1697
Data Index: 3272625 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5479. Min Act: -0.1700
Data Index: 6697481 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5479. Min Act: -0.1700
Data Index: 8278378 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5303. Min Act: -0.1700
Data Index: 6083349 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5303. Min Act: -0.1699
Data Index: 1420840 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5303. Min Act: -0.1700
Data Index: 7098729 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5303. Min Act: -0.1541
Data Index: 6880179 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.4953. Min Act: -0.1698
Data Index: 6610281 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5128. Min Act: -0.1699
Data Index: 6156725 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6352. Min Range: -1.6352
Max Act: 1.5128. Min Act: -0.1692
Data Index: 1430194 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19