Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2704. Min Range: -12.2704
Max Act: 12.2704. Min Act: -0.1700
Data Index: 26968 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2704. Min Range: -12.2704
Max Act: 11.2704. Min Act: -0.1700
Data Index: 161334 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.8954. Min Act: -0.1700
Data Index: 5921783 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.9579. Min Act: -0.1700
Data Index: 8005098 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.9579. Min Act: -0.1700
Data Index: 6360668 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.9579. Min Act: -0.1700
Data Index: 7552424 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.8954. Min Act: -0.1700
Data Index: 4307015 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.8954. Min Act: -0.1700
Data Index: 5449909 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.8329. Min Act: -0.1700
Data Index: 4338920 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.7704. Min Act: -0.1700
Data Index: 5825806 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.7704. Min Act: -0.1700
Data Index: 6004284 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.7704. Min Act: -0.1700
Data Index: 5027330 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.7079. Min Act: -0.1700
Data Index: 2869018 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.7079. Min Act: -0.1700
Data Index: 3756591 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.7079. Min Act: -0.1700
Data Index: 512803 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.7079. Min Act: -0.1700
Data Index: 7293930 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.7079. Min Act: -0.1700
Data Index: 3569820 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.6454. Min Act: -0.1700
Data Index: 3358681 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.5829. Min Act: -0.1700
Data Index: 2555077 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2704. Min Range: -12.2704
Max Act: 10.5829. Min Act: -0.1700
Data Index: 2671478 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19