Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.8253. Min Act: -0.1700
Data Index: 2748950 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.7315. Min Act: -0.1700
Data Index: 58447 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.3565. Min Act: -0.1700
Data Index: 5739111 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.3253. Min Act: -0.1700
Data Index: 8453407 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.2940. Min Act: -0.1700
Data Index: 3510828 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.2628. Min Act: -0.1700
Data Index: 2168392 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.2003. Min Act: -0.1700
Data Index: 676209 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.1690. Min Act: -0.1700
Data Index: 4471428 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.1690. Min Act: -0.1700
Data Index: 128830 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0753. Min Act: -0.1700
Data Index: 1882490 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0753. Min Act: -0.1700
Data Index: 8367752 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0440. Min Act: -0.1700
Data Index: 3468651 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0128. Min Act: -0.1700
Data Index: 7712412 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0440. Min Act: -0.1700
Data Index: 6584587 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0440. Min Act: -0.1700
Data Index: 1345777 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0440. Min Act: -0.1700
Data Index: 4826782 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0440. Min Act: -0.1700
Data Index: 341992 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0440. Min Act: -0.1700
Data Index: 1200672 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0440. Min Act: -0.1700
Data Index: 3102674 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8253. Min Range: -6.8253
Max Act: 6.0128. Min Act: -0.1700
Data Index: 6231871 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19