Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 274 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.3606. Min Act: -0.1700
Data Index: 937833 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.2035. Min Act: -0.1700
Data Index: 603022 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.2192. Min Act: -0.1700
Data Index: 1137926 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.1877. Min Act: -0.1700
Data Index: 435979 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.1877. Min Act: -0.1700
Data Index: 564872 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.1720. Min Act: -0.1700
Data Index: 1221874 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.1563. Min Act: -0.1700
Data Index: 1348647 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.1563. Min Act: -0.1700
Data Index: 540860 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.1090. Min Act: -0.1700
Data Index: 194385 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.1247. Min Act: -0.1700
Data Index: 377938 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0932. Min Act: -0.1700
Data Index: 643733 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0932. Min Act: -0.1700
Data Index: 1158214 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0459. Min Act: -0.1700
Data Index: 623748 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0617. Min Act: -0.1700
Data Index: 1198821 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0459. Min Act: -0.1700
Data Index: 37332 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0459. Min Act: -0.1700
Data Index: 306310 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0617. Min Act: -0.1700
Data Index: 1138943 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0459. Min Act: -0.1700
Data Index: 959223 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0143. Min Act: -0.1700
Data Index: 1069115 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3606. Min Range: -3.3606
Max Act: 3.0301. Min Act: -0.1700
Data Index: 356748 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19