Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3878. Min Range: -7.3878
Max Act: 7.3878. Min Act: -0.1700
Data Index: 2375822 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3878. Min Range: -7.3878
Max Act: 7.3566. Min Act: -0.1700
Data Index: 3807600 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3878. Min Range: -7.3878
Max Act: 7.1066. Min Act: -0.1700
Data Index: 3577278 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3878. Min Range: -7.3878
Max Act: 7.0441. Min Act: -0.1700
Data Index: 4241407 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.9503. Min Act: -0.1700
Data Index: 2776916 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.9816. Min Act: -0.1700
Data Index: 8296309 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.8878. Min Act: -0.1700
Data Index: 4445762 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.7628. Min Act: -0.1700
Data Index: 4374886 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.7941. Min Act: -0.1700
Data Index: 4197189 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.7316. Min Act: -0.1700
Data Index: 2240173 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.7316. Min Act: -0.1700
Data Index: 7678173 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.7003. Min Act: -0.1700
Data Index: 7791815 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.7316. Min Act: -0.1700
Data Index: 1646760 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.6691. Min Act: -0.1700
Data Index: 4813988 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.6691. Min Act: -0.1700
Data Index: 2993830 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.6691. Min Act: -0.1700
Data Index: 6275326 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.6378. Min Act: -0.1700
Data Index: 1700997 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.6378. Min Act: -0.1700
Data Index: 7366200 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.5753. Min Act: -0.1700
Data Index: 4457098 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3878. Min Range: -7.3878
Max Act: 6.6066. Min Act: -0.1700
Data Index: 7607710 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19