Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6025 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3041. Min Range: -6.3041
Max Act: 6.3041. Min Act: -0.1700
Data Index: 6126677 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3041. Min Range: -6.3041
Max Act: 6.2728. Min Act: -0.1700
Data Index: 4088601 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3041. Min Range: -6.3041
Max Act: 6.1166. Min Act: -0.1700
Data Index: 4604141 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3041. Min Range: -6.3041
Max Act: 6.0228. Min Act: -0.1700
Data Index: 1860906 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3041. Min Range: -6.3041
Max Act: 6.0228. Min Act: -0.1700
Data Index: 4088602 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9916. Min Act: -0.1700
Data Index: 691936 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9603. Min Act: -0.1700
Data Index: 3055201 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9603. Min Act: -0.1700
Data Index: 4035152 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9603. Min Act: -0.1700
Data Index: 2410992 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9291. Min Act: -0.1700
Data Index: 6125964 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9291. Min Act: -0.1700
Data Index: 7922390 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9291. Min Act: -0.1700
Data Index: 7228187 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9291. Min Act: -0.1700
Data Index: 3694864 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9291. Min Act: -0.1700
Data Index: 5049391 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9291. Min Act: -0.1700
Data Index: 8181521 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.9291. Min Act: -0.1700
Data Index: 6404041 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.8666. Min Act: -0.1700
Data Index: 1556735 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.8666. Min Act: -0.1700
Data Index: 5972906 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.8666. Min Act: -0.1700
Data Index: 3681979 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3041. Min Range: -6.3041
Max Act: 5.8353. Min Act: -0.1700
Data Index: 3246363 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19