Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2609 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.7725. Min Act: -0.1700
Data Index: 3424380 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.7413. Min Act: -0.1697
Data Index: 3030639 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6788. Min Act: -0.1699
Data Index: 5124156 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6163. Min Act: -0.1700
Data Index: 8705878 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6163. Min Act: -0.1700
Data Index: 1292055 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6163. Min Act: -0.1700
Data Index: 1427543 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.6163. Min Act: -0.1700
Data Index: 7141088 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5850. Min Act: -0.1700
Data Index: 7700834 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5538. Min Act: -0.1700
Data Index: 4675376 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5538. Min Act: -0.1700
Data Index: 4477321 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5538. Min Act: -0.1700
Data Index: 3208941 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5538. Min Act: -0.1700
Data Index: 3956093 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5538. Min Act: -0.1700
Data Index: 6811477 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5538. Min Act: -0.1700
Data Index: 7115587 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5225. Min Act: -0.1700
Data Index: 238833 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.5225. Min Act: -0.1700
Data Index: 653274 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4913. Min Act: -0.1700
Data Index: 3251026 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4913. Min Act: -0.1700
Data Index: 5402936 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4913. Min Act: -0.1700
Data Index: 6078829 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7725. Min Range: -5.7725
Max Act: 5.4913. Min Act: -0.1700
Data Index: 2924606 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19