Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4343 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2689. Min Range: -4.2689
Max Act: 4.2689. Min Act: -0.1700
Data Index: 6712137 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2689. Min Range: -4.2689
Max Act: 4.0189. Min Act: -0.1700
Data Index: 7440270 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.9251. Min Act: -0.1700
Data Index: 11669 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.8938. Min Act: -0.1700
Data Index: 4049230 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.8782. Min Act: -0.1700
Data Index: 6270232 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.8782. Min Act: -0.1700
Data Index: 7621354 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.8313. Min Act: -0.1700
Data Index: 4594396 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.8313. Min Act: -0.1700
Data Index: 4369401 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7844. Min Act: -0.1700
Data Index: 5419995 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7844. Min Act: -0.1700
Data Index: 732456 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7844. Min Act: -0.1700
Data Index: 8533519 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7687. Min Act: -0.1700
Data Index: 6480698 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7531. Min Act: -0.1700
Data Index: 7474747 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7687. Min Act: -0.1700
Data Index: 7295884 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7531. Min Act: -0.1700
Data Index: 540537 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7375. Min Act: -0.1700
Data Index: 7885255 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7218. Min Act: -0.1700
Data Index: 6074757 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7062. Min Act: -0.1700
Data Index: 4521925 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7218. Min Act: -0.1700
Data Index: 2012775 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2689. Min Range: -4.2689
Max Act: 3.7375. Min Act: -0.1700
Data Index: 2646026 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19