Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.9163. Min Range: -14.9163
Max Act: 14.9163. Min Act: -0.1700
Data Index: 7558832 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.9163. Min Range: -14.9163
Max Act: 14.4163. Min Act: -0.1700
Data Index: 8406766 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.7913. Min Act: -0.1700
Data Index: 7619032 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.7288. Min Act: -0.1700
Data Index: 6174272 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.6663. Min Act: -0.1700
Data Index: 7899821 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.6663. Min Act: -0.1700
Data Index: 8728432 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 18165 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.5413. Min Act: -0.1700
Data Index: 8007362 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.5413. Min Act: -0.1700
Data Index: 8284391 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.4788. Min Act: -0.1700
Data Index: 5179278 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.4163. Min Act: -0.1700
Data Index: 3192967 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.3538. Min Act: -0.1700
Data Index: 5641985 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.3538. Min Act: -0.1700
Data Index: 650299 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.2913. Min Act: -0.1700
Data Index: 5677959 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.2913. Min Act: -0.1700
Data Index: 6026836 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.2913. Min Act: -0.1700
Data Index: 1145547 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.2288. Min Act: -0.1700
Data Index: 1853015 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.2288. Min Act: -0.1700
Data Index: 5359865 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.2288. Min Act: -0.1700
Data Index: 5395928 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.9163. Min Range: -14.9163
Max Act: 13.2288. Min Act: -0.1700
Data Index: 3715792 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19