Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2204 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.6153. Min Act: -0.1700
Data Index: 1018188 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.4903. Min Act: -0.1700
Data Index: 740778 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.4590. Min Act: -0.1700
Data Index: 6896595 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.4590. Min Act: -0.1700
Data Index: 7406936 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.4903. Min Act: -0.1700
Data Index: 1088348 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.4590. Min Act: -0.1700
Data Index: 1098908 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3965. Min Act: -0.1700
Data Index: 7371256 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3653. Min Act: -0.1700
Data Index: 3355974 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3653. Min Act: -0.1700
Data Index: 4194064 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3340. Min Act: -0.1700
Data Index: 2256906 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3340. Min Act: -0.1700
Data Index: 312686 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3028. Min Act: -0.1700
Data Index: 1038960 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3028. Min Act: -0.1700
Data Index: 6953408 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3028. Min Act: -0.1700
Data Index: 3235040 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.3028. Min Act: -0.1700
Data Index: 3323859 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.2715. Min Act: -0.1700
Data Index: 1932265 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.2403. Min Act: -0.1700
Data Index: 3404633 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.2715. Min Act: -0.1700
Data Index: 5733258 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.2715. Min Act: -0.1700
Data Index: 6004433 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6153. Min Range: -4.6153
Max Act: 4.2715. Min Act: -0.1700
Data Index: 6152772 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19