Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 971 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.7222. Min Act: -0.1700
Data Index: 1383691 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.6910. Min Act: -0.1700
Data Index: 196419 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.4722. Min Act: -0.1700
Data Index: 4405316 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.4410. Min Act: -0.1700
Data Index: 8800602 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.4097. Min Act: -0.1700
Data Index: 70702 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.4097. Min Act: -0.1700
Data Index: 3454896 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.3785. Min Act: -0.1700
Data Index: 8403655 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.3785. Min Act: -0.1700
Data Index: 3128425 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.3472. Min Act: -0.1700
Data Index: 3369932 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2847. Min Act: -0.1700
Data Index: 1167215 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2847. Min Act: -0.1700
Data Index: 4963947 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2847. Min Act: -0.1700
Data Index: 1518520 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2847. Min Act: -0.1700
Data Index: 7651950 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2847. Min Act: -0.1700
Data Index: 6854386 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2534. Min Act: -0.1700
Data Index: 4858341 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2534. Min Act: -0.1700
Data Index: 3873454 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2534. Min Act: -0.1700
Data Index: 122093 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2222. Min Act: -0.1700
Data Index: 5504066 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2222. Min Act: -0.1700
Data Index: 4377401 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7222. Min Range: -4.7222
Max Act: 4.2534. Min Act: -0.1700
Data Index: 5909465 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19