Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1359 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.6318. Min Act: -0.1700
Data Index: 3396032 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.5380. Min Act: -0.1700
Data Index: 6900831 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.4755. Min Act: -0.1700
Data Index: 8103284 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.4442. Min Act: -0.1700
Data Index: 7249008 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.5068. Min Act: -0.1700
Data Index: 8527388 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.4755. Min Act: -0.1700
Data Index: 7164387 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.4442. Min Act: -0.1700
Data Index: 635389 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.3505. Min Act: -0.1700
Data Index: 2973694 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.3817. Min Act: -0.1700
Data Index: 3499886 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.2880. Min Act: -0.1700
Data Index: 6388198 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.3192. Min Act: -0.1700
Data Index: 682970 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.3505. Min Act: -0.1700
Data Index: 7143986 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.2880. Min Act: -0.1700
Data Index: 7327442 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.3192. Min Act: -0.1700
Data Index: 3499798 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.2567. Min Act: -0.1700
Data Index: 1871430 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.2255. Min Act: -0.1700
Data Index: 2458733 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.2567. Min Act: -0.1700
Data Index: 6701494 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.2567. Min Act: -0.1700
Data Index: 4227048 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.2567. Min Act: -0.1700
Data Index: 1016883 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6318. Min Range: -4.6318
Max Act: 4.2255. Min Act: -0.1700
Data Index: 607268 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19