Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4618 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1352. Min Act: -0.1700
Data Index: 2340406 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1039. Min Act: -0.1700
Data Index: 7089236 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8852. Min Act: -0.1700
Data Index: 5665519 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8852. Min Act: -0.1700
Data Index: 1284773 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8539. Min Act: -0.1700
Data Index: 8801497 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8539. Min Act: -0.1700
Data Index: 4382158 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8539. Min Act: -0.1700
Data Index: 3076863 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 992995 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 3754333 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7914. Min Act: -0.1700
Data Index: 8810316 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7289. Min Act: -0.1700
Data Index: 7839303 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 5697659 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4252893 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7914. Min Act: -0.1700
Data Index: 1678404 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 3948714 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 550801 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 1090942 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 2421382 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 35912 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6664. Min Act: -0.1700
Data Index: 6841500 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19