Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3255 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.3826. Min Act: -0.1700
Data Index: 2133617 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3826. Min Range: -6.3826
Max Act: 6.1638. Min Act: -0.1700
Data Index: 2342361 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.9451. Min Act: -0.1700
Data Index: 4525093 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.7888. Min Act: -0.1700
Data Index: 2444024 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.6326. Min Act: -0.1700
Data Index: 1821030 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.5701. Min Act: -0.1700
Data Index: 7874425 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.5388. Min Act: -0.1700
Data Index: 6728430 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.5076. Min Act: -0.1700
Data Index: 2599999 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.4763. Min Act: -0.1700
Data Index: 5049128 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.4138. Min Act: -0.1700
Data Index: 3271389 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3826. Min Act: -0.1700
Data Index: 455579 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3826. Min Act: -0.1700
Data Index: 8325248 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3826. Min Act: -0.1700
Data Index: 7050661 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3826. Min Act: -0.1700
Data Index: 409384 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3826. Min Act: -0.1700
Data Index: 976710 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3826. Min Act: -0.1700
Data Index: 3144 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3513. Min Act: -0.1700
Data Index: 2876238 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3513. Min Act: -0.1700
Data Index: 3320963 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3513. Min Act: -0.1700
Data Index: 6655092 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3826. Min Range: -6.3826
Max Act: 5.3201. Min Act: -0.1700
Data Index: 865625 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19