Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0270. Min Range: -8.0270
Max Act: 8.0270. Min Act: -0.1700
Data Index: 4607979 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.9645. Min Act: -0.1700
Data Index: 1263555 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.8082. Min Act: -0.1700
Data Index: 1237908 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.7457. Min Act: -0.1700
Data Index: 7356573 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.7457. Min Act: -0.1700
Data Index: 4450543 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.6832. Min Act: -0.1700
Data Index: 8760166 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.6832. Min Act: -0.1700
Data Index: 1892452 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.6520. Min Act: -0.1700
Data Index: 2586705 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.6207. Min Act: -0.1700
Data Index: 915694 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.6207. Min Act: -0.1700
Data Index: 7543466 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.6207. Min Act: -0.1700
Data Index: 1051179 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.5582. Min Act: -0.1700
Data Index: 6972812 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.5270. Min Act: -0.1700
Data Index: 4152176 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.4957. Min Act: -0.1700
Data Index: 7037699 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.4645. Min Act: -0.1700
Data Index: 3766531 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.4645. Min Act: -0.1700
Data Index: 4217660 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.4645. Min Act: -0.1700
Data Index: 5270981 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.4332. Min Act: -0.1700
Data Index: 6655098 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.4332. Min Act: -0.1700
Data Index: 6102901 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0270. Min Range: -8.0270
Max Act: 7.4645. Min Act: -0.1700
Data Index: 5184348 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19