Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 585 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2406. Min Range: -8.2406
Max Act: 8.2406. Min Act: -0.1700
Data Index: 783560 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2406. Min Range: -8.2406
Max Act: 8.2406. Min Act: -0.1700
Data Index: 4562815 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2406. Min Range: -8.2406
Max Act: 8.2093. Min Act: -0.1700
Data Index: 5166617 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2406. Min Range: -8.2406
Max Act: 8.1781. Min Act: -0.1700
Data Index: 469608 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2406. Min Range: -8.2406
Max Act: 8.1468. Min Act: -0.1700
Data Index: 6298786 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2406. Min Range: -8.2406
Max Act: 8.1156. Min Act: -0.1700
Data Index: 7135470 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2406. Min Range: -8.2406
Max Act: 8.0531. Min Act: -0.1700
Data Index: 6358039 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.9281. Min Act: -0.1700
Data Index: 8778794 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.8343. Min Act: -0.1700
Data Index: 1160701 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.8343. Min Act: -0.1700
Data Index: 3705281 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.6156. Min Act: -0.1700
Data Index: 919087 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.5843. Min Act: -0.1700
Data Index: 1249328 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.6156. Min Act: -0.1700
Data Index: 1251062 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.4593. Min Act: -0.1700
Data Index: 3989939 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.4281. Min Act: -0.1700
Data Index: 2347768 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.3968. Min Act: -0.1700
Data Index: 3082738 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.3656. Min Act: -0.1700
Data Index: 2600089 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.3656. Min Act: -0.1700
Data Index: 4906458 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.3343. Min Act: -0.1700
Data Index: 2992134 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2406. Min Range: -8.2406
Max Act: 7.2406. Min Act: -0.1700
Data Index: 1851963 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19