Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2879 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2726. Min Act: -0.1700
Data Index: 5608620 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2638. Min Act: -0.1700
Data Index: 5989929 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2550. Min Act: -0.1700
Data Index: 135644 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 7089413 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 645347 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 2344675 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 5670169 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 7996999 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 763106 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 5608619 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 1248941 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 1187108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2462. Min Act: -0.1700
Data Index: 4380090 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2286. Min Act: -0.1700
Data Index: 6775641 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2198. Min Act: -0.1700
Data Index: 8195623 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2198. Min Act: -0.1700
Data Index: 8507527 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2198. Min Act: -0.1700
Data Index: 1708340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2198. Min Act: -0.1700
Data Index: 5247643 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2286. Min Act: -0.1700
Data Index: 8524894 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2726. Min Range: -1.2726
Max Act: 1.2198. Min Act: -0.1700
Data Index: 4081899 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19