Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.4193. Min Act: -0.1700
Data Index: 1854484 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.3255. Min Act: -0.1700
Data Index: 7280832 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.3255. Min Act: -0.1700
Data Index: 2488970 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.2005. Min Act: -0.1700
Data Index: 5307717 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.1693. Min Act: -0.1700
Data Index: 4497532 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.1380. Min Act: -0.1700
Data Index: 389900 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.0755. Min Act: -0.1700
Data Index: 4659571 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.0443. Min Act: -0.1700
Data Index: 4875454 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.0130. Min Act: -0.1700
Data Index: 5897280 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.0130. Min Act: -0.1700
Data Index: 208531 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4193. Min Range: -6.4193
Max Act: 6.0130. Min Act: -0.1700
Data Index: 389896 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.9818. Min Act: -0.1700
Data Index: 1034168 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.9818. Min Act: -0.1700
Data Index: 5951600 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.9505. Min Act: -0.1700
Data Index: 2186101 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.9505. Min Act: -0.1700
Data Index: 2687219 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.9193. Min Act: -0.1700
Data Index: 2410993 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.8568. Min Act: -0.1700
Data Index: 3474959 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.8568. Min Act: -0.1700
Data Index: 2036942 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.8255. Min Act: -0.1700
Data Index: 74019 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4193. Min Range: -6.4193
Max Act: 5.8255. Min Act: -0.1700
Data Index: 5080487 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19