Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3388 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.5778. Min Act: -0.1700
Data Index: 8110369 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.5465. Min Act: -0.1700
Data Index: 694589 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.5153. Min Act: -0.1700
Data Index: 2849246 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.5153. Min Act: -0.1700
Data Index: 292959 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.4840. Min Act: -0.1700
Data Index: 464326 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.4528. Min Act: -0.1700
Data Index: 8204132 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.4528. Min Act: -0.1700
Data Index: 694580 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.4215. Min Act: -0.1700
Data Index: 4659029 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3903. Min Act: -0.1700
Data Index: 8075226 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3903. Min Act: -0.1700
Data Index: 5625623 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.4215. Min Act: -0.1700
Data Index: 1103934 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3903. Min Act: -0.1700
Data Index: 3557308 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3590. Min Act: -0.1700
Data Index: 5647740 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3278. Min Act: -0.1700
Data Index: 4256926 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3278. Min Act: -0.1700
Data Index: 1864456 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3278. Min Act: -0.1700
Data Index: 2294029 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3278. Min Act: -0.1700
Data Index: 649368 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3278. Min Act: -0.1700
Data Index: 7185938 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.2965. Min Act: -0.1700
Data Index: 2610605 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5778. Min Range: -4.5778
Max Act: 4.3278. Min Act: -0.1700
Data Index: 7353430 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19