Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 533 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3397. Min Range: -7.3397
Max Act: 7.3397. Min Act: -0.1700
Data Index: 4210143 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3397. Min Range: -7.3397
Max Act: 7.1522. Min Act: -0.1700
Data Index: 7819349 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3397. Min Range: -7.3397
Max Act: 7.1209. Min Act: -0.1700
Data Index: 4623924 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3397. Min Range: -7.3397
Max Act: 7.0584. Min Act: -0.1700
Data Index: 4711421 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3397. Min Range: -7.3397
Max Act: 7.0272. Min Act: -0.1700
Data Index: 4929275 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.9959. Min Act: -0.1700
Data Index: 836780 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.9959. Min Act: -0.1700
Data Index: 2476646 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.9022. Min Act: -0.1700
Data Index: 7882289 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.9022. Min Act: -0.1700
Data Index: 3461620 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.9022. Min Act: -0.1700
Data Index: 5008659 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.8397. Min Act: -0.1700
Data Index: 6948332 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.8709. Min Act: -0.1700
Data Index: 4100472 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.9022. Min Act: -0.1700
Data Index: 3838903 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.8397. Min Act: -0.1700
Data Index: 8087119 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.8084. Min Act: -0.1700
Data Index: 7601030 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.7772. Min Act: -0.1700
Data Index: 7559970 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.7147. Min Act: -0.1700
Data Index: 6536537 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.7147. Min Act: -0.1700
Data Index: 8263915 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.7147. Min Act: -0.1700
Data Index: 2107968 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3397. Min Range: -7.3397
Max Act: 6.7147. Min Act: -0.1700
Data Index: 1608834 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19