Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4849 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1282. Min Range: -6.1282
Max Act: 6.1282. Min Act: -0.1700
Data Index: 8310875 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.9719. Min Act: -0.1700
Data Index: 8689741 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.9407. Min Act: -0.1700
Data Index: 5659676 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.9094. Min Act: -0.1700
Data Index: 3774035 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.8782. Min Act: -0.1700
Data Index: 2632577 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.8157. Min Act: -0.1700
Data Index: 601021 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.8157. Min Act: -0.1700
Data Index: 2852317 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.7532. Min Act: -0.1700
Data Index: 1971377 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.7532. Min Act: -0.1700
Data Index: 789382 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.7219. Min Act: -0.1700
Data Index: 69770 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.6907. Min Act: -0.1700
Data Index: 1198588 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.6594. Min Act: -0.1700
Data Index: 653300 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.6594. Min Act: -0.1700
Data Index: 7832181 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.6594. Min Act: -0.1700
Data Index: 653007 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.5969. Min Act: -0.1700
Data Index: 4535199 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.6282. Min Act: -0.1700
Data Index: 1582395 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.6282. Min Act: -0.1700
Data Index: 4142155 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.6282. Min Act: -0.1700
Data Index: 5200367 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.6282. Min Act: -0.1700
Data Index: 4533881 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1282. Min Range: -6.1282
Max Act: 5.5657. Min Act: -0.1700
Data Index: 4787502 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19