Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.4843. Min Act: -0.1700
Data Index: 5227412 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.4218. Min Act: -0.1700
Data Index: 1476919 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.4218. Min Act: -0.1700
Data Index: 4406331 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.3593. Min Act: -0.1700
Data Index: 7627465 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.2968. Min Act: -0.1700
Data Index: 5058917 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.2343. Min Act: -0.1700
Data Index: 3121731 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.2343. Min Act: -0.1700
Data Index: 1777518 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.2343. Min Act: -0.1700
Data Index: 3584327 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.2343. Min Act: -0.1700
Data Index: 6607407 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.2343. Min Act: -0.1700
Data Index: 3612565 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1718. Min Act: -0.1700
Data Index: 7131217 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1718. Min Act: -0.1700
Data Index: 1155733 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1718. Min Act: -0.1700
Data Index: 3696845 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1718. Min Act: -0.1700
Data Index: 6850980 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1718. Min Act: -0.1700
Data Index: 8404781 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1718. Min Act: -0.1700
Data Index: 593299 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1718. Min Act: -0.1700
Data Index: 593297 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1718. Min Act: -0.1700
Data Index: 7407949 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1093. Min Act: -0.1700
Data Index: 6151606 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4843. Min Range: -7.4843
Max Act: 7.1093. Min Act: -0.1700
Data Index: 4061131 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19