Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5926 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.9202. Min Act: -0.1700
Data Index: 5164444 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4514. Min Act: -0.1700
Data Index: 6598185 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4202. Min Act: -0.1700
Data Index: 1679611 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.4202. Min Act: -0.1700
Data Index: 6384356 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.3889. Min Act: -0.1700
Data Index: 6438748 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.3264. Min Act: -0.1700
Data Index: 6401803 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.2952. Min Act: -0.1700
Data Index: 2951964 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.2639. Min Act: -0.1700
Data Index: 6731896 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.2014. Min Act: -0.1700
Data Index: 7321721 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.2327. Min Act: -0.1700
Data Index: 7548687 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.2014. Min Act: -0.1700
Data Index: 1932850 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.1702. Min Act: -0.1700
Data Index: 6329613 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.1389. Min Act: -0.1700
Data Index: 400906 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.1076. Min Act: -0.1700
Data Index: 1774231 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.1076. Min Act: -0.1700
Data Index: 2705215 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.1702. Min Act: -0.1700
Data Index: 1366162 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.1076. Min Act: -0.1700
Data Index: 8464285 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.1076. Min Act: -0.1700
Data Index: 2492967 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.0764. Min Act: -0.1700
Data Index: 8499215 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9202. Min Range: -4.9202
Max Act: 4.0451. Min Act: -0.1700
Data Index: 7505099 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19