Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5382 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1419. Min Range: -6.1419
Max Act: 6.1419. Min Act: -0.1700
Data Index: 618056 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1419. Min Range: -6.1419
Max Act: 6.0481. Min Act: -0.1700
Data Index: 7662123 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1419. Min Range: -6.1419
Max Act: 6.0481. Min Act: -0.1700
Data Index: 73498 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.9231. Min Act: -0.1700
Data Index: 2407956 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.8919. Min Act: -0.1700
Data Index: 199728 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.9231. Min Act: -0.1700
Data Index: 2336255 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.8606. Min Act: -0.1700
Data Index: 722002 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.8606. Min Act: -0.1700
Data Index: 112939 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.8606. Min Act: -0.1700
Data Index: 1178867 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7981. Min Act: -0.1700
Data Index: 393166 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7669. Min Act: -0.1700
Data Index: 6443284 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7669. Min Act: -0.1700
Data Index: 5883489 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7356. Min Act: -0.1700
Data Index: 420368 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7356. Min Act: -0.1700
Data Index: 8724865 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7356. Min Act: -0.1700
Data Index: 2024840 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7356. Min Act: -0.1700
Data Index: 6766503 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7044. Min Act: -0.1700
Data Index: 2233003 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.7356. Min Act: -0.1700
Data Index: 8517988 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.6419. Min Act: -0.1700
Data Index: 1972640 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1419. Min Range: -6.1419
Max Act: 5.6419. Min Act: -0.1700
Data Index: 2283391 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19