Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 635 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.6910. Min Act: -0.1700
Data Index: 1181318 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.5660. Min Act: -0.1700
Data Index: 7840605 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.5973. Min Act: -0.1700
Data Index: 5991067 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.5660. Min Act: -0.1700
Data Index: 8447694 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.4410. Min Act: -0.1700
Data Index: 5214454 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.4410. Min Act: -0.1700
Data Index: 6326928 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.4098. Min Act: -0.1700
Data Index: 2720066 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.4098. Min Act: -0.1700
Data Index: 2981449 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.4098. Min Act: -0.1700
Data Index: 3351347 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.3785. Min Act: -0.1700
Data Index: 5969766 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.3785. Min Act: -0.1700
Data Index: 1440611 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.3785. Min Act: -0.1700
Data Index: 8411605 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.3160. Min Act: -0.1700
Data Index: 1633848 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.3160. Min Act: -0.1700
Data Index: 3836307 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.2848. Min Act: -0.1700
Data Index: 4457585 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.3160. Min Act: -0.1700
Data Index: 787004 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.2848. Min Act: -0.1700
Data Index: 330972 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.2848. Min Act: -0.1700
Data Index: 7819186 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.2848. Min Act: -0.1700
Data Index: 573002 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6910. Min Range: -6.6910
Max Act: 6.2848. Min Act: -0.1700
Data Index: 2374082 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19