Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.5789. Min Act: -0.1700
Data Index: 1595779 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.5477. Min Act: -0.1700
Data Index: 5702409 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.5477. Min Act: -0.1700
Data Index: 5325043 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.5164. Min Act: -0.1700
Data Index: 5436863 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.5164. Min Act: -0.1700
Data Index: 838510 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4539. Min Act: -0.1700
Data Index: 5302576 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4539. Min Act: -0.1700
Data Index: 5702401 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4539. Min Act: -0.1700
Data Index: 1323147 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4227. Min Act: -0.1700
Data Index: 609812 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4227. Min Act: -0.1700
Data Index: 2092552 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.4539. Min Act: -0.1700
Data Index: 5702402 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3914. Min Act: -0.1700
Data Index: 6280494 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3914. Min Act: -0.1700
Data Index: 2105985 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3914. Min Act: -0.1700
Data Index: 316883 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3602. Min Act: -0.1700
Data Index: 2384932 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3914. Min Act: -0.1700
Data Index: 1023625 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3602. Min Act: -0.1700
Data Index: 699551 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3602. Min Act: -0.1700
Data Index: 4883072 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3602. Min Act: -0.1700
Data Index: 1133904 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5789. Min Range: -5.5789
Max Act: 5.3602. Min Act: -0.1700
Data Index: 4931677 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19