Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.4635. Min Act: -0.1700
Data Index: 3381563 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.2448. Min Act: -0.1700
Data Index: 6998999 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.1823. Min Act: -0.1700
Data Index: 5394555 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.1510. Min Act: -0.1700
Data Index: 6032 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.1510. Min Act: -0.1700
Data Index: 5131658 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9948. Min Act: -0.1700
Data Index: 5638017 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.0260. Min Act: -0.1700
Data Index: 6402527 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.0260. Min Act: -0.1700
Data Index: 2114356 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9635. Min Act: -0.1700
Data Index: 3095923 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9635. Min Act: -0.1700
Data Index: 2307424 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9635. Min Act: -0.1700
Data Index: 4691818 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9323. Min Act: -0.1700
Data Index: 8680636 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9323. Min Act: -0.1700
Data Index: 401258 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9323. Min Act: -0.1700
Data Index: 8766792 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9323. Min Act: -0.1700
Data Index: 4934891 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9323. Min Act: -0.1700
Data Index: 676185 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9010. Min Act: -0.1700
Data Index: 3251722 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9010. Min Act: -0.1700
Data Index: 3361455 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9010. Min Act: -0.1700
Data Index: 2450949 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9010. Min Act: -0.1700
Data Index: 3891467 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19