Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 466 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2471. Min Range: -10.2471
Max Act: 10.2471. Min Act: -0.1700
Data Index: 6821877 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2471. Min Range: -10.2471
Max Act: 10.1846. Min Act: -0.1700
Data Index: 4367971 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2471. Min Range: -10.2471
Max Act: 10.1221. Min Act: -0.1700
Data Index: 1681487 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.9971. Min Act: -0.1700
Data Index: 2374230 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.9971. Min Act: -0.1700
Data Index: 7309786 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.9346. Min Act: -0.1700
Data Index: 8177375 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.8721. Min Act: -0.1700
Data Index: 3906597 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.8096. Min Act: -0.1700
Data Index: 4189637 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.8096. Min Act: -0.1700
Data Index: 4273841 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.8096. Min Act: -0.1700
Data Index: 4532138 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.7471. Min Act: -0.1700
Data Index: 44977 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.6846. Min Act: -0.1700
Data Index: 7132504 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.6221. Min Act: -0.1700
Data Index: 8579096 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.6221. Min Act: -0.1700
Data Index: 2363196 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.6221. Min Act: -0.1700
Data Index: 8788716 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.6221. Min Act: -0.1700
Data Index: 6150974 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.5596. Min Act: -0.1700
Data Index: 2424058 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.4971. Min Act: -0.1700
Data Index: 662189 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.3721. Min Act: -0.1700
Data Index: 8074107 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2471. Min Range: -10.2471
Max Act: 9.4346. Min Act: -0.1700
Data Index: 780557 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19