Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.8741. Min Act: -0.1700
Data Index: 134361 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.8116. Min Act: -0.1700
Data Index: 7068098 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.8116. Min Act: -0.1700
Data Index: 3042790 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.7491. Min Act: -0.1700
Data Index: 8168992 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.7178. Min Act: -0.1700
Data Index: 2345672 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.6553. Min Act: -0.1700
Data Index: 3376407 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.6553. Min Act: -0.1700
Data Index: 4140879 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.6241. Min Act: -0.1700
Data Index: 8708449 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.6241. Min Act: -0.1700
Data Index: 8288682 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.6241. Min Act: -0.1700
Data Index: 7669667 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5928. Min Act: -0.1700
Data Index: 83064 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5616. Min Act: -0.1700
Data Index: 6207564 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5616. Min Act: -0.1700
Data Index: 4504999 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5303. Min Act: -0.1700
Data Index: 1735739 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5303. Min Act: -0.1700
Data Index: 3700760 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5303. Min Act: -0.1700
Data Index: 4802906 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.5303. Min Act: -0.1700
Data Index: 6868467 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.4991. Min Act: -0.1700
Data Index: 5161231 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.4991. Min Act: -0.1700
Data Index: 4256192 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8741. Min Range: -5.8741
Max Act: 5.4991. Min Act: -0.1700
Data Index: 8340520 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19