Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0717. Min Range: -4.0717
Max Act: 4.0717. Min Act: -0.1700
Data Index: 5226875 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.9153. Min Act: -0.1700
Data Index: 4884300 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.9153. Min Act: -0.1700
Data Index: 8237058 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.8841. Min Act: -0.1700
Data Index: 6699830 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.9153. Min Act: -0.1700
Data Index: 4438666 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.8528. Min Act: -0.1700
Data Index: 2889814 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.8215. Min Act: -0.1700
Data Index: 2808916 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.8215. Min Act: -0.1700
Data Index: 4039611 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7590. Min Act: -0.1700
Data Index: 6220101 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7590. Min Act: -0.1700
Data Index: 551974 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7746. Min Act: -0.1700
Data Index: 762079 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7746. Min Act: -0.1700
Data Index: 2846877 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7434. Min Act: -0.1700
Data Index: 7639814 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7277. Min Act: -0.1700
Data Index: 2997896 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7277. Min Act: -0.1700
Data Index: 6329736 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7277. Min Act: -0.1700
Data Index: 4908838 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7277. Min Act: -0.1700
Data Index: 4327661 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7277. Min Act: -0.1700
Data Index: 8252716 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.7434. Min Act: -0.1700
Data Index: 2557086 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0717. Min Range: -4.0717
Max Act: 3.6808. Min Act: -0.1700
Data Index: 6264642 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19