Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3744 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.5425. Min Act: -0.1700
Data Index: 911492 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.4800. Min Act: -0.1700
Data Index: 4538804 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.4800. Min Act: -0.1700
Data Index: 2553483 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.4488. Min Act: -0.1700
Data Index: 4892431 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3863. Min Act: -0.1700
Data Index: 5310303 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.4488. Min Act: -0.1700
Data Index: 815462 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3863. Min Act: -0.1700
Data Index: 4874419 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3863. Min Act: -0.1700
Data Index: 8341249 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3863. Min Act: -0.1700
Data Index: 4660283 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3863. Min Act: -0.1700
Data Index: 1285696 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3550. Min Act: -0.1700
Data Index: 8566095 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3238. Min Act: -0.1700
Data Index: 5013453 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3238. Min Act: -0.1700
Data Index: 6615607 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.2925. Min Act: -0.1700
Data Index: 1244297 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.3238. Min Act: -0.1700
Data Index: 3862982 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.2925. Min Act: -0.1700
Data Index: 5154418 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.2925. Min Act: -0.1700
Data Index: 1922432 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.2925. Min Act: -0.1700
Data Index: 4467554 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.2613. Min Act: -0.1700
Data Index: 1544012 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5425. Min Range: -5.5425
Max Act: 5.2925. Min Act: -0.1700
Data Index: 2449 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19