Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 199 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.9545. Min Act: -0.1700
Data Index: 1565961 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.8607. Min Act: -0.1700
Data Index: 3537832 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.7043. Min Act: -0.1700
Data Index: 3242170 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.6730. Min Act: -0.1700
Data Index: 1987647 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.7043. Min Act: -0.1700
Data Index: 2786752 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.7043. Min Act: -0.1700
Data Index: 2842066 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.6730. Min Act: -0.1700
Data Index: 2958657 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.6417. Min Act: -0.1700
Data Index: 4153549 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.6417. Min Act: -0.1700
Data Index: 5295948 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.6261. Min Act: -0.1700
Data Index: 701740 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.6104. Min Act: -0.1700
Data Index: 5961653 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5948. Min Act: -0.1700
Data Index: 3105536 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5948. Min Act: -0.1700
Data Index: 3179163 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5635. Min Act: -0.1700
Data Index: 4021475 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5478. Min Act: -0.1700
Data Index: 1231242 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5478. Min Act: -0.1700
Data Index: 7023795 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5322. Min Act: -0.1700
Data Index: 1530589 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5478. Min Act: -0.1700
Data Index: 3717338 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5165. Min Act: -0.1700
Data Index: 5470554 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9545. Min Range: -3.9545
Max Act: 3.5008. Min Act: -0.1700
Data Index: 5246259 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19