Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6365. Min Range: -9.6365
Max Act: 9.6365. Min Act: -0.1700
Data Index: 2287025 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6365. Min Range: -9.6365
Max Act: 9.3865. Min Act: -0.1700
Data Index: 4522071 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6365. Min Range: -9.6365
Max Act: 9.2615. Min Act: -0.1700
Data Index: 8553452 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6365. Min Range: -9.6365
Max Act: 9.2615. Min Act: -0.1700
Data Index: 2015520 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6365. Min Range: -9.6365
Max Act: 9.1365. Min Act: -0.1700
Data Index: 269125 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6365. Min Range: -9.6365
Max Act: 9.0740. Min Act: -0.1700
Data Index: 4229785 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6365. Min Range: -9.6365
Max Act: 9.0115. Min Act: -0.1700
Data Index: 1755263 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.9490. Min Act: -0.1700
Data Index: 1054671 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.9490. Min Act: -0.1700
Data Index: 5808558 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.9490. Min Act: -0.1700
Data Index: 2385711 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.9490. Min Act: -0.1700
Data Index: 4153499 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.9490. Min Act: -0.1700
Data Index: 2331194 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.9490. Min Act: -0.1700
Data Index: 7866888 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.8865. Min Act: -0.1700
Data Index: 2745952 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.8865. Min Act: -0.1700
Data Index: 6789523 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.8240. Min Act: -0.1700
Data Index: 8415591 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.8240. Min Act: -0.1700
Data Index: 8470704 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.7615. Min Act: -0.1700
Data Index: 4990793 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.7615. Min Act: -0.1700
Data Index: 4328900 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6365. Min Range: -9.6365
Max Act: 8.7615. Min Act: -0.1700
Data Index: 5838518 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19