Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5470 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.8601. Min Act: -0.1700
Data Index: 3342584 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.8289. Min Act: -0.1697
Data Index: 8030146 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.7351. Min Act: -0.1700
Data Index: 7526032 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.7351. Min Act: -0.1700
Data Index: 7520893 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.7039. Min Act: -0.1700
Data Index: 4913900 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.7039. Min Act: -0.1700
Data Index: 8748454 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6726. Min Act: -0.1700
Data Index: 1911307 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6726. Min Act: -0.1700
Data Index: 6074846 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6726. Min Act: -0.1700
Data Index: 300580 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6726. Min Act: -0.1699
Data Index: 4913911 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6726. Min Act: -0.1700
Data Index: 7256615 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6414. Min Act: -0.1698
Data Index: 1216140 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6414. Min Act: -0.1700
Data Index: 371971 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6101. Min Act: -0.1696
Data Index: 2014176 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6414. Min Act: -0.1700
Data Index: 2055449 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6101. Min Act: -0.1700
Data Index: 7259245 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6101. Min Act: -0.1700
Data Index: 6494690 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6414. Min Act: -0.1700
Data Index: 89748 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6101. Min Act: -0.1691
Data Index: 1954623 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8601. Min Range: -5.8601
Max Act: 5.6101. Min Act: -0.1700
Data Index: 6545229 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19