Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3781 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3920. Min Range: -6.3920
Max Act: 6.3920. Min Act: -0.1700
Data Index: 2159364 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3920. Min Range: -6.3920
Max Act: 6.1733. Min Act: -0.1700
Data Index: 299558 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9858. Min Act: -0.1700
Data Index: 50520 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3920. Min Range: -6.3920
Max Act: 6.0170. Min Act: -0.1700
Data Index: 4295658 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9545. Min Act: -0.1700
Data Index: 4924599 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9545. Min Act: -0.1700
Data Index: 6081195 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9545. Min Act: -0.1700
Data Index: 5131651 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9545. Min Act: -0.1700
Data Index: 3285011 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9858. Min Act: -0.1700
Data Index: 1526269 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9545. Min Act: -0.1700
Data Index: 368440 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9233. Min Act: -0.1700
Data Index: 2283335 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9233. Min Act: -0.1700
Data Index: 441065 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.8920. Min Act: -0.1700
Data Index: 7847493 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.8920. Min Act: -0.1700
Data Index: 7184504 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.8608. Min Act: -0.1700
Data Index: 7720816 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.9233. Min Act: -0.1700
Data Index: 197404 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.8920. Min Act: -0.1700
Data Index: 51900 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.8608. Min Act: -0.1700
Data Index: 2894267 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.7983. Min Act: -0.1700
Data Index: 2339350 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3920. Min Range: -6.3920
Max Act: 5.8295. Min Act: -0.1700
Data Index: 3698195 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19