Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.8176. Min Act: -0.1700
Data Index: 3821735 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.5363. Min Act: -0.1700
Data Index: 3901987 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.5051. Min Act: -0.1700
Data Index: 8685332 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.4738. Min Act: -0.1700
Data Index: 5688883 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.4738. Min Act: -0.1700
Data Index: 82356 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3801. Min Act: -0.1700
Data Index: 2388670 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3801. Min Act: -0.1700
Data Index: 7727365 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3801. Min Act: -0.1700
Data Index: 3926621 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3488. Min Act: -0.1700
Data Index: 209453 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3488. Min Act: -0.1700
Data Index: 8384913 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3176. Min Act: -0.1700
Data Index: 3165784 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3176. Min Act: -0.1700
Data Index: 4126909 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.2863. Min Act: -0.1700
Data Index: 2623415 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3176. Min Act: -0.1700
Data Index: 5910047 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.3176. Min Act: -0.1700
Data Index: 4390179 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.2863. Min Act: -0.1700
Data Index: 4173846 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.2863. Min Act: -0.1700
Data Index: 2904478 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.2863. Min Act: -0.1700
Data Index: 7139480 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.2863. Min Act: -0.1700
Data Index: 5357581 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8176. Min Range: -6.8176
Max Act: 6.2863. Min Act: -0.1700
Data Index: 4167478 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19