Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1063. Min Range: -8.1063
Max Act: 8.1063. Min Act: -0.1700
Data Index: 7233531 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.7938. Min Act: -0.1700
Data Index: 288200 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.7000. Min Act: -0.1700
Data Index: 5687543 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.3875. Min Act: -0.1700
Data Index: 6385352 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.3563. Min Act: -0.1700
Data Index: 1490266 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.3250. Min Act: -0.1700
Data Index: 1199178 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.3250. Min Act: -0.1700
Data Index: 7992583 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.3250. Min Act: -0.1700
Data Index: 7716683 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.2313. Min Act: -0.1700
Data Index: 8432883 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.2000. Min Act: -0.1700
Data Index: 8181046 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.2000. Min Act: -0.1700
Data Index: 7161218 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.1688. Min Act: -0.1700
Data Index: 4052065 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.1063. Min Act: -0.1700
Data Index: 5403479 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.1375. Min Act: -0.1700
Data Index: 2339672 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.1063. Min Act: -0.1700
Data Index: 5302110 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.1063. Min Act: -0.1700
Data Index: 8696869 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.1063. Min Act: -0.1700
Data Index: 4849850 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.0750. Min Act: -0.1700
Data Index: 6051938 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.0750. Min Act: -0.1700
Data Index: 1685471 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1063. Min Range: -8.1063
Max Act: 7.0750. Min Act: -0.1700
Data Index: 5805391 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19