Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4915 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0532. Min Range: -1.0532

Max Act: 1.0532. Min Act: -0.0000

Data Index: 484932 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 1.0532. Min Range: -1.0532

Max Act: 1.0270. Min Act: -0.0000

Data Index: 51637 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9664. Min Act: -0.0000

Data Index: 140188 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9424. Min Act: -0.0000

Data Index: 984556 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1180158 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1160979 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8756. Min Act: -0.0000

Data Index: 486371 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1302090 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8222. Min Act: -0.0000

Data Index: 762690 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8183. Min Act: -0.0000

Data Index: 385445 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7665. Min Act: -0.0000

Data Index: 73700 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1359570 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7407. Min Act: -0.0000

Data Index: 622621 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1118530 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1513301 (Python Code)

Max Activating Token Index: 726

Text #15

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7759. Min Act: -0.0000

Data Index: 517946 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7692. Min Act: -0.0000

Data Index: 477138 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1228874 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7641. Min Act: -0.0000

Data Index: 109526 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1100176 (C4 (Web Text))

Max Activating Token Index: 224