Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.7082. Min Act: -0.1700
Data Index: 3615855 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.6457. Min Act: -0.1700
Data Index: 211412 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.6457. Min Act: -0.1700
Data Index: 3615856 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.5832. Min Act: -0.1700
Data Index: 4439366 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.5207. Min Act: -0.1700
Data Index: 819187 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.5207. Min Act: -0.1700
Data Index: 6316488 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.4582. Min Act: -0.1700
Data Index: 423737 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.3957. Min Act: -0.1700
Data Index: 2830567 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.3957. Min Act: -0.1700
Data Index: 2551285 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.3957. Min Act: -0.1700
Data Index: 2003796 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.3332. Min Act: -0.1700
Data Index: 4013093 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.3332. Min Act: -0.1700
Data Index: 5839954 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.3019. Min Act: -0.1700
Data Index: 8526416 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.2707. Min Act: -0.1700
Data Index: 8213237 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.2707. Min Act: -0.1700
Data Index: 771538 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.2707. Min Act: -0.1700
Data Index: 5630551 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.2707. Min Act: -0.1700
Data Index: 7107330 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.2707. Min Act: -0.1700
Data Index: 3993825 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.2707. Min Act: -0.1700
Data Index: 4439043 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7082. Min Range: -5.7082
Max Act: 5.2707. Min Act: -0.1700
Data Index: 8365176 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19