Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1162 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.6191. Min Act: -0.1700
Data Index: 4649097 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.5667. Min Act: -0.1700
Data Index: 4244174 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.5317. Min Act: -0.1699
Data Index: 4643139 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.4966. Min Act: -0.1700
Data Index: 2999797 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.4966. Min Act: -0.1700
Data Index: 3145658 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.4966. Min Act: -0.1700
Data Index: 5636708 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.4790. Min Act: -0.1700
Data Index: 8206169 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.4439. Min Act: -0.1700
Data Index: 2095763 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.4263. Min Act: -0.1699
Data Index: 8355400 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3910. Min Act: -0.1700
Data Index: 558825 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3734. Min Act: -0.1700
Data Index: 875366 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3734. Min Act: -0.1699
Data Index: 8120020 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3558. Min Act: -0.1697
Data Index: 4244191 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3558. Min Act: -0.1700
Data Index: 3661112 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3558. Min Act: -0.1700
Data Index: 6633307 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3381. Min Act: -0.1700
Data Index: 4471929 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3381. Min Act: -0.1700
Data Index: 3778490 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3205. Min Act: -0.1700
Data Index: 8206175 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3205. Min Act: -0.1700
Data Index: 452428 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6191. Min Range: -1.6191
Max Act: 1.3028. Min Act: -0.1700
Data Index: 2857537 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19