Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.7725. Min Act: -0.1700
Data Index: 5295074 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.7100. Min Act: -0.1700
Data Index: 6964470 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.6162. Min Act: -0.1700
Data Index: 8336479 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.5225. Min Act: -0.1700
Data Index: 6798024 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.4600. Min Act: -0.1700
Data Index: 5529612 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.4600. Min Act: -0.1700
Data Index: 2604277 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.4287. Min Act: -0.1700
Data Index: 4184606 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3975. Min Act: -0.1700
Data Index: 5529611 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3975. Min Act: -0.1700
Data Index: 5196389 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3975. Min Act: -0.1700
Data Index: 1236100 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3975. Min Act: -0.1700
Data Index: 3742605 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3662. Min Act: -0.1700
Data Index: 297505 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3662. Min Act: -0.1700
Data Index: 5214714 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3350. Min Act: -0.1700
Data Index: 6378347 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3350. Min Act: -0.1700
Data Index: 5376790 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3037. Min Act: -0.1700
Data Index: 436508 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.2725. Min Act: -0.1700
Data Index: 8709863 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3037. Min Act: -0.1700
Data Index: 809380 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.3037. Min Act: -0.1700
Data Index: 2494152 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7725. Min Range: -4.7725
Max Act: 4.2725. Min Act: -0.1700
Data Index: 6220959 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19