Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1314 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.4292. Min Act: -0.1559
Data Index: 6489946 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3764. Min Act: -0.1469
Data Index: 7447288 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3675. Min Act: -0.1700
Data Index: 2176972 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3587. Min Act: -0.1700
Data Index: 5319494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3411. Min Act: -0.1517
Data Index: 8035778 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3499. Min Act: -0.1694
Data Index: 1340941 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3499. Min Act: -0.1653
Data Index: 3669927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3499. Min Act: -0.1494
Data Index: 1135982 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3411. Min Act: -0.1226
Data Index: 707121 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3323. Min Act: -0.1611
Data Index: 3471624 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3323. Min Act: -0.1534
Data Index: 8215847 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3323. Min Act: -0.1692
Data Index: 2218295 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3323. Min Act: -0.1591
Data Index: 3069197 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3235. Min Act: -0.1523
Data Index: 2054300 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3323. Min Act: -0.1674
Data Index: 4931035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3146. Min Act: -0.1321
Data Index: 7775334 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3323. Min Act: -0.1697
Data Index: 7548520 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3146. Min Act: -0.1642
Data Index: 2162619 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3235. Min Act: -0.1622
Data Index: 2430566 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4292. Min Range: -1.4292
Max Act: 1.3235. Min Act: -0.1642
Data Index: 4345501 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19