Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1189 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.7779. Min Act: -0.1700
Data Index: 786710 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.6178. Min Act: -0.1700
Data Index: 1643421 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5695. Min Act: -0.1700
Data Index: 1311570 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5856. Min Act: -0.1700
Data Index: 1492662 (Python Code)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5534. Min Act: -0.1700
Data Index: 1451530 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5856. Min Act: -0.1700
Data Index: 1082541 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5372. Min Act: -0.1700
Data Index: 1488476 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5372. Min Act: -0.1700
Data Index: 868726 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5211. Min Act: -0.1700
Data Index: 1479601 (Python Code)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5049. Min Act: -0.1700
Data Index: 1299727 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5211. Min Act: -0.1700
Data Index: 1576858 (Python Code)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5049. Min Act: -0.1700
Data Index: 273620 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5049. Min Act: -0.1700
Data Index: 918783 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.5049. Min Act: -0.1700
Data Index: 1142252 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.4887. Min Act: -0.1700
Data Index: 947795 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.4725. Min Act: -0.1700
Data Index: 1483159 (Python Code)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.4562. Min Act: -0.1700
Data Index: 173426 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.4562. Min Act: -0.1700
Data Index: 593389 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.4562. Min Act: -0.1700
Data Index: 1552046 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7779. Min Range: -2.7779
Max Act: 2.4725. Min Act: -0.1700
Data Index: 1531479 (Python Code)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19