Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1685. Min Range: -8.1685
Max Act: 8.1685. Min Act: -0.1700
Data Index: 6847735 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1685. Min Range: -8.1685
Max Act: 7.6373. Min Act: -0.1700
Data Index: 7137623 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1685. Min Range: -8.1685
Max Act: 7.1998. Min Act: -0.1700
Data Index: 1149398 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.9498. Min Act: -0.1700
Data Index: 3510020 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.9185. Min Act: -0.1700
Data Index: 5178521 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.8560. Min Act: -0.1700
Data Index: 103928 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.8248. Min Act: -0.1700
Data Index: 327002 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.8248. Min Act: -0.1700
Data Index: 1310779 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.8248. Min Act: -0.1700
Data Index: 2149922 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.8248. Min Act: -0.1700
Data Index: 7649132 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.8248. Min Act: -0.1700
Data Index: 5448595 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.7623. Min Act: -0.1700
Data Index: 961821 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.7623. Min Act: -0.1700
Data Index: 5440912 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.7623. Min Act: -0.1700
Data Index: 4027140 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.7310. Min Act: -0.1700
Data Index: 7016198 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.7310. Min Act: -0.1700
Data Index: 702336 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.6685. Min Act: -0.1700
Data Index: 5216048 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.7310. Min Act: -0.1700
Data Index: 2103356 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.6998. Min Act: -0.1700
Data Index: 4712415 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1685. Min Range: -8.1685
Max Act: 6.6685. Min Act: -0.1700
Data Index: 2586361 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19