Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0324. Min Range: -4.0324
Max Act: 4.0324. Min Act: -0.1700
Data Index: 7598527 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.9230. Min Act: -0.1700
Data Index: 3219554 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.9073. Min Act: -0.1700
Data Index: 1637742 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8917. Min Act: -0.1700
Data Index: 8739534 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8917. Min Act: -0.1700
Data Index: 4777692 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8761. Min Act: -0.1700
Data Index: 7105477 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8604. Min Act: -0.1700
Data Index: 4251567 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8448. Min Act: -0.1700
Data Index: 5584184 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8448. Min Act: -0.1700
Data Index: 1586152 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8292. Min Act: -0.1700
Data Index: 4672712 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8604. Min Act: -0.1700
Data Index: 43635 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8292. Min Act: -0.1700
Data Index: 8111534 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8135. Min Act: -0.1700
Data Index: 8186509 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8292. Min Act: -0.1700
Data Index: 4119951 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8135. Min Act: -0.1700
Data Index: 2899528 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8135. Min Act: -0.1700
Data Index: 932583 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.8135. Min Act: -0.1700
Data Index: 2082120 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.7979. Min Act: -0.1700
Data Index: 535098 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.7822. Min Act: -0.1700
Data Index: 2147544 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0324. Min Range: -4.0324
Max Act: 3.7979. Min Act: -0.1700
Data Index: 1506850 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19