Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5613 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.9590. Min Act: -0.1700
Data Index: 3234986 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.9277. Min Act: -0.1700
Data Index: 4194189 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.7715. Min Act: -0.1700
Data Index: 6189011 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.7090. Min Act: -0.1700
Data Index: 4007050 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.6465. Min Act: -0.1700
Data Index: 5468123 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.6152. Min Act: -0.1700
Data Index: 3785624 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.6465. Min Act: -0.1700
Data Index: 1892613 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.5840. Min Act: -0.1700
Data Index: 380618 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.5527. Min Act: -0.1700
Data Index: 7222677 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.5527. Min Act: -0.1700
Data Index: 1190292 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.5527. Min Act: -0.1700
Data Index: 564191 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.5215. Min Act: -0.1700
Data Index: 3920989 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.5215. Min Act: -0.1700
Data Index: 2588438 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.4902. Min Act: -0.1700
Data Index: 4567387 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.4902. Min Act: -0.1700
Data Index: 6457360 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.5215. Min Act: -0.1700
Data Index: 7624485 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.5215. Min Act: -0.1700
Data Index: 7664140 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.4277. Min Act: -0.1700
Data Index: 7044046 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.4277. Min Act: -0.1700
Data Index: 6483487 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9590. Min Range: -6.9590
Max Act: 6.4277. Min Act: -0.1700
Data Index: 5018036 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19