Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1976 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.8589. Min Act: -0.1700
Data Index: 3005380 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.7339. Min Act: -0.1700
Data Index: 2166275 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.7339. Min Act: -0.1700
Data Index: 5125837 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.7027. Min Act: -0.1700
Data Index: 5228893 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.7027. Min Act: -0.1700
Data Index: 7097021 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.7027. Min Act: -0.1700
Data Index: 2993280 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.6714. Min Act: -0.1700
Data Index: 8165387 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.6714. Min Act: -0.1700
Data Index: 2340408 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.6714. Min Act: -0.1700
Data Index: 3524783 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.6402. Min Act: -0.1700
Data Index: 341789 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.6714. Min Act: -0.1700
Data Index: 8103531 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.6089. Min Act: -0.1700
Data Index: 8230784 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.6089. Min Act: -0.1700
Data Index: 8130543 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.5777. Min Act: -0.1700
Data Index: 3749139 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.5777. Min Act: -0.1700
Data Index: 3385603 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.5777. Min Act: -0.1699
Data Index: 5943007 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.5464. Min Act: -0.1700
Data Index: 1313494 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.5464. Min Act: -0.1700
Data Index: 137171 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.5464. Min Act: -0.1700
Data Index: 957415 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8589. Min Range: -5.8589
Max Act: 5.5152. Min Act: -0.1700
Data Index: 3114881 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19