Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5673 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1122. Min Range: -9.1122
Max Act: 9.1122. Min Act: -0.1700
Data Index: 3598842 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.9247. Min Act: -0.1700
Data Index: 4207701 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.9872. Min Act: -0.1700
Data Index: 4207704 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.8622. Min Act: -0.1700
Data Index: 4283305 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.9247. Min Act: -0.1700
Data Index: 4207702 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.7372. Min Act: -0.1700
Data Index: 3598844 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.6122. Min Act: -0.1700
Data Index: 5346171 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.6122. Min Act: -0.1700
Data Index: 3406527 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.5497. Min Act: -0.1700
Data Index: 5409635 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.4872. Min Act: -0.1700
Data Index: 3598841 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.4872. Min Act: -0.1700
Data Index: 6244612 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.4247. Min Act: -0.1700
Data Index: 1406548 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.4247. Min Act: -0.1700
Data Index: 3324179 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.3934. Min Act: -0.1700
Data Index: 5409636 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.3309. Min Act: -0.1700
Data Index: 4283308 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.3622. Min Act: -0.1700
Data Index: 4630652 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.2372. Min Act: -0.1700
Data Index: 8087070 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.2372. Min Act: -0.1699
Data Index: 8087069 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.2684. Min Act: -0.1700
Data Index: 315172 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1122. Min Range: -9.1122
Max Act: 8.2059. Min Act: -0.1700
Data Index: 2018517 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19