Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2223 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1411. Min Range: -8.1411
Max Act: 8.1411. Min Act: -0.1700
Data Index: 2624377 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.8286. Min Act: -0.1700
Data Index: 6148913 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.8286. Min Act: -0.1700
Data Index: 3633855 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7661. Min Act: -0.1700
Data Index: 3833077 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7661. Min Act: -0.1700
Data Index: 560185 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7036. Min Act: -0.1700
Data Index: 3171316 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7661. Min Act: -0.1700
Data Index: 2414484 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7661. Min Act: -0.1700
Data Index: 6705718 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7661. Min Act: -0.1700
Data Index: 4787957 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7036. Min Act: -0.1700
Data Index: 6774352 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7036. Min Act: -0.1700
Data Index: 870938 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7036. Min Act: -0.1700
Data Index: 494944 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7036. Min Act: -0.1700
Data Index: 3364406 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7036. Min Act: -0.1700
Data Index: 7937436 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.7036. Min Act: -0.1700
Data Index: 745138 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.6411. Min Act: -0.1700
Data Index: 7407370 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.6411. Min Act: -0.1700
Data Index: 7490857 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.6411. Min Act: -0.1700
Data Index: 1620542 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.6411. Min Act: -0.1700
Data Index: 1931484 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1411. Min Range: -8.1411
Max Act: 7.6411. Min Act: -0.1700
Data Index: 6837017 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19