Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4720 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0427. Min Range: -1.0427

Max Act: 1.0427. Min Act: -0.0000

Data Index: 525330 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.8751. Min Act: -0.0000

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.8933. Min Act: -0.0000

Data Index: 158399 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.8804. Min Act: -0.0000

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7673. Min Act: 0.0000

Data Index: 355855 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7975. Min Act: -0.0000

Data Index: 316944 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.8264. Min Act: -0.0000

Data Index: 422502 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7661. Min Act: -0.0000

Data Index: 303655 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7555. Min Act: -0.0000

Data Index: 639115 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7530. Min Act: -0.0000

Data Index: 912585 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7812. Min Act: -0.0000

Data Index: 959419 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1184785 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7115. Min Act: 0.0000

Data Index: 190136 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1353494 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6978. Min Act: -0.0000

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7225. Min Act: -0.0000

Data Index: 72851 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7218. Min Act: -0.0000

Data Index: 624898 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6267. Min Act: 0.0000

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6148. Min Act: -0.0000

Data Index: 271451 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.5835. Min Act: -0.0000

Data Index: 253758 (C4 (Web Text))

Max Activating Token Index: 324