Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5362 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.8835. Min Act: -0.1700
Data Index: 6240125 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.7585. Min Act: -0.1700
Data Index: 1931504 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.7273. Min Act: -0.1700
Data Index: 8352135 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.6960. Min Act: -0.1700
Data Index: 2663448 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.6648. Min Act: -0.1700
Data Index: 8284348 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.6335. Min Act: -0.1700
Data Index: 3216049 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.6648. Min Act: -0.1700
Data Index: 4955921 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.6335. Min Act: -0.1700
Data Index: 6095846 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.5710. Min Act: -0.1700
Data Index: 7369042 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.6023. Min Act: -0.1700
Data Index: 5068140 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.6023. Min Act: -0.1700
Data Index: 2891080 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.5398. Min Act: -0.1700
Data Index: 3216048 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.5710. Min Act: -0.1700
Data Index: 2290784 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.5710. Min Act: -0.1700
Data Index: 6228645 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.5710. Min Act: -0.1700
Data Index: 684822 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.4773. Min Act: -0.1700
Data Index: 3099254 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.5085. Min Act: -0.1700
Data Index: 4440371 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.5085. Min Act: -0.1700
Data Index: 1144506 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.4773. Min Act: -0.1700
Data Index: 2793322 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8835. Min Range: -6.8835
Max Act: 6.4773. Min Act: -0.1700
Data Index: 779854 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19