Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2470 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4250. Min Range: -7.4250
Max Act: 7.4250. Min Act: -0.1700
Data Index: 3029055 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4250. Min Range: -7.4250
Max Act: 7.1438. Min Act: -0.1700
Data Index: 6586478 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4250. Min Range: -7.4250
Max Act: 7.0813. Min Act: -0.1700
Data Index: 4606471 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4250. Min Range: -7.4250
Max Act: 7.0188. Min Act: -0.1700
Data Index: 6078028 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.9563. Min Act: -0.1700
Data Index: 4671914 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.6750. Min Act: -0.1700
Data Index: 3919748 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.6438. Min Act: -0.1700
Data Index: 8464929 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.5500. Min Act: -0.1700
Data Index: 6763838 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.5500. Min Act: -0.1700
Data Index: 5640213 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.5188. Min Act: -0.1700
Data Index: 1758644 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.4875. Min Act: -0.1700
Data Index: 5575591 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.4875. Min Act: -0.1700
Data Index: 1355978 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.4875. Min Act: -0.1697
Data Index: 2319534 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.4250. Min Act: -0.1700
Data Index: 3995323 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.4563. Min Act: -0.1700
Data Index: 8270230 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.4250. Min Act: -0.1700
Data Index: 5006023 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.3938. Min Act: -0.1700
Data Index: 1136607 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.3625. Min Act: -0.1700
Data Index: 5005079 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.3313. Min Act: -0.1700
Data Index: 668152 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4250. Min Range: -7.4250
Max Act: 6.3625. Min Act: -0.1700
Data Index: 2376619 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19