Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.2977. Min Act: -0.1700
Data Index: 1933531 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0789. Min Act: -0.1700
Data Index: 1617686 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0789. Min Act: -0.1700
Data Index: 3730174 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0476. Min Act: -0.1700
Data Index: 3969348 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0164. Min Act: -0.1700
Data Index: 5367061 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0164. Min Act: -0.1700
Data Index: 5367060 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0164. Min Act: -0.1700
Data Index: 1933534 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0164. Min Act: -0.1700
Data Index: 5679215 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9851. Min Act: -0.1700
Data Index: 5679212 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9851. Min Act: -0.1700
Data Index: 88164 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9851. Min Act: -0.1700
Data Index: 161732 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9851. Min Act: -0.1700
Data Index: 3693783 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9851. Min Act: -0.1700
Data Index: 161734 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9538. Min Act: -0.1700
Data Index: 4611875 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9538. Min Act: -0.1700
Data Index: 515446 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9226. Min Act: -0.1700
Data Index: 8087125 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9226. Min Act: -0.1700
Data Index: 7782505 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9226. Min Act: -0.1700
Data Index: 7541792 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9226. Min Act: -0.1700
Data Index: 3879268 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9226. Min Act: -0.1700
Data Index: 5868566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19