Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.9410. Min Act: -0.1681
Data Index: 6501924 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.9723. Min Act: -0.1700
Data Index: 3719244 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.9410. Min Act: -0.1700
Data Index: 128295 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.8785. Min Act: -0.1700
Data Index: 441470 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.9098. Min Act: -0.1700
Data Index: 128298 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.8160. Min Act: -0.1700
Data Index: 4860337 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.8160. Min Act: -0.1700
Data Index: 5192415 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.8473. Min Act: -0.1687
Data Index: 7225622 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.7535. Min Act: -0.1692
Data Index: 1887799 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.7535. Min Act: -0.1700
Data Index: 239848 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.7535. Min Act: -0.1697
Data Index: 3252324 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.7223. Min Act: -0.1700
Data Index: 5934648 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.6285. Min Act: -0.1699
Data Index: 5934646 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.6285. Min Act: -0.1699
Data Index: 2240978 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.6285. Min Act: -0.1700
Data Index: 7861259 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.6285. Min Act: -0.1700
Data Index: 7249880 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.5660. Min Act: -0.1700
Data Index: 3719241 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.5660. Min Act: -0.1700
Data Index: 2629429 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.5348. Min Act: -0.1699
Data Index: 1887802 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9723. Min Range: -4.9723
Max Act: 4.5348. Min Act: -0.1700
Data Index: 4749276 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19