Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3752 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.9446. Min Act: -0.1700
Data Index: 7379283 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.9446. Min Act: -0.1700
Data Index: 6315178 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.9604. Min Act: -0.1700
Data Index: 4619756 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.9446. Min Act: -0.1700
Data Index: 4429839 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.9446. Min Act: -0.1700
Data Index: 5757793 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8970. Min Act: -0.1700
Data Index: 2350402 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.9129. Min Act: -0.1700
Data Index: 6351673 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8812. Min Act: -0.1700
Data Index: 6491543 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8970. Min Act: -0.1700
Data Index: 8325434 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8812. Min Act: -0.1700
Data Index: 429201 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8653. Min Act: -0.1700
Data Index: 8511368 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8653. Min Act: -0.1700
Data Index: 5634727 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8653. Min Act: -0.1700
Data Index: 6208600 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8494. Min Act: -0.1700
Data Index: 362176 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8335. Min Act: -0.1700
Data Index: 2950611 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8494. Min Act: -0.1700
Data Index: 1183488 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8335. Min Act: -0.1700
Data Index: 2678456 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8335. Min Act: -0.1700
Data Index: 2482413 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8176. Min Act: -0.1700
Data Index: 5354999 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9604. Min Range: -2.9604
Max Act: 2.8017. Min Act: -0.1700
Data Index: 7272884 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19