Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5105 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.5090. Min Act: -0.1700
Data Index: 3086912 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.3215. Min Act: -0.1700
Data Index: 488495 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.3215. Min Act: -0.1700
Data Index: 8555179 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.3215. Min Act: -0.1700
Data Index: 169756 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.3215. Min Act: -0.1700
Data Index: 5546820 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.2902. Min Act: -0.1700
Data Index: 3557343 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.2277. Min Act: -0.1700
Data Index: 2848616 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.2277. Min Act: -0.1700
Data Index: 2787368 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.1965. Min Act: -0.1700
Data Index: 5035371 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.1965. Min Act: -0.1700
Data Index: 8051127 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.1652. Min Act: -0.1700
Data Index: 1771593 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.1652. Min Act: -0.1700
Data Index: 3076220 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.1652. Min Act: -0.1700
Data Index: 5646301 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.1339. Min Act: -0.1700
Data Index: 2720654 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.1027. Min Act: -0.1700
Data Index: 7805862 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.1027. Min Act: -0.1700
Data Index: 8689193 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.0402. Min Act: -0.1700
Data Index: 3560851 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.0714. Min Act: -0.1700
Data Index: 1201836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.0714. Min Act: -0.1700
Data Index: 7198226 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5090. Min Range: -4.5090
Max Act: 4.0714. Min Act: -0.1700
Data Index: 6807797 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19