Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4108. Min Range: -7.4108
Max Act: 7.4108. Min Act: -0.1700
Data Index: 5353832 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4108. Min Range: -7.4108
Max Act: 7.2233. Min Act: -0.1700
Data Index: 8819564 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4108. Min Range: -7.4108
Max Act: 7.0983. Min Act: -0.1700
Data Index: 6184901 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.9733. Min Act: -0.1700
Data Index: 8403103 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.9108. Min Act: -0.1700
Data Index: 5235333 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.8796. Min Act: -0.1700
Data Index: 5719371 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.8483. Min Act: -0.1700
Data Index: 8725235 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.8483. Min Act: -0.1700
Data Index: 3203969 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.8171. Min Act: -0.1700
Data Index: 7957263 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.8483. Min Act: -0.1700
Data Index: 4045600 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.7233. Min Act: -0.1700
Data Index: 2442095 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.7233. Min Act: -0.1700
Data Index: 6249928 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.6608. Min Act: -0.1700
Data Index: 3697137 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.6608. Min Act: -0.1700
Data Index: 3823493 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.6608. Min Act: -0.1700
Data Index: 2025791 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.6296. Min Act: -0.1700
Data Index: 6851224 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.6296. Min Act: -0.1700
Data Index: 4279658 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.5358. Min Act: -0.1700
Data Index: 1199235 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.5046. Min Act: -0.1700
Data Index: 6308298 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4108. Min Range: -7.4108
Max Act: 6.5358. Min Act: -0.1700
Data Index: 3825950 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19