Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8720. Min Act: -0.1700
Data Index: 3511858 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8720. Min Act: -0.1700
Data Index: 7171836 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8549. Min Act: -0.1700
Data Index: 1917950 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8378. Min Act: -0.1700
Data Index: 6626213 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8378. Min Act: -0.1700
Data Index: 641350 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8378. Min Act: -0.1700
Data Index: 385231 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8378. Min Act: -0.1700
Data Index: 3063686 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8378. Min Act: -0.1700
Data Index: 8718307 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8378. Min Act: -0.1700
Data Index: 8274821 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8206. Min Act: -0.1700
Data Index: 8447228 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8206. Min Act: -0.1700
Data Index: 1759001 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8206. Min Act: -0.1700
Data Index: 6087143 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8206. Min Act: -0.1700
Data Index: 3081985 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8206. Min Act: -0.1700
Data Index: 7862034 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8035. Min Act: -0.1700
Data Index: 6376443 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8035. Min Act: -0.1700
Data Index: 749630 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8035. Min Act: -0.1700
Data Index: 2913766 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8035. Min Act: -0.1700
Data Index: 6742453 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8035. Min Act: -0.1700
Data Index: 3676288 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8720. Min Range: -1.8720
Max Act: 1.8035. Min Act: -0.1700
Data Index: 6889268 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19