Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3794 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.4852. Min Act: -0.1700
Data Index: 448111 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.2977. Min Act: -0.1700
Data Index: 6189671 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.2977. Min Act: -0.1700
Data Index: 3142820 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.2039. Min Act: -0.1700
Data Index: 1730360 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.2039. Min Act: -0.1700
Data Index: 7789920 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.1414. Min Act: -0.1700
Data Index: 1514163 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.0789. Min Act: -0.1700
Data Index: 6018904 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.0477. Min Act: -0.1700
Data Index: 1685235 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9852. Min Act: -0.1700
Data Index: 7777305 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4852. Min Range: -5.4852
Max Act: 5.0164. Min Act: -0.1700
Data Index: 6018906 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9852. Min Act: -0.1700
Data Index: 431604 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9852. Min Act: -0.1700
Data Index: 6501497 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9852. Min Act: -0.1700
Data Index: 1576045 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9539. Min Act: -0.1700
Data Index: 2902618 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9539. Min Act: -0.1700
Data Index: 2888782 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9539. Min Act: -0.1700
Data Index: 412134 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9539. Min Act: -0.1700
Data Index: 8103768 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9227. Min Act: -0.1700
Data Index: 6419625 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9227. Min Act: -0.1700
Data Index: 8475024 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4852. Min Range: -5.4852
Max Act: 4.9227. Min Act: -0.1700
Data Index: 4755548 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19