Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5626 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1670. Min Range: -8.1670
Max Act: 8.1670. Min Act: -0.1700
Data Index: 5196139 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.9170. Min Act: -0.1700
Data Index: 2827292 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.8545. Min Act: -0.1700
Data Index: 382761 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.7295. Min Act: -0.1700
Data Index: 4490799 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.7295. Min Act: -0.1700
Data Index: 1613561 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.7295. Min Act: -0.1700
Data Index: 5583276 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.7295. Min Act: -0.1700
Data Index: 7453171 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.6670. Min Act: -0.1700
Data Index: 597568 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.6670. Min Act: -0.1700
Data Index: 6349065 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.6670. Min Act: -0.1700
Data Index: 6948899 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.6045. Min Act: -0.1700
Data Index: 3894195 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.6045. Min Act: -0.1700
Data Index: 943284 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.6045. Min Act: -0.1700
Data Index: 3971100 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.5733. Min Act: -0.1700
Data Index: 6562829 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.5733. Min Act: -0.1700
Data Index: 6419787 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.5420. Min Act: -0.1700
Data Index: 5573875 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.5420. Min Act: -0.1700
Data Index: 3405327 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.5420. Min Act: -0.1700
Data Index: 6939064 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.5108. Min Act: -0.1700
Data Index: 730798 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1670. Min Range: -8.1670
Max Act: 7.4795. Min Act: -0.1700
Data Index: 6620054 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19