Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2029 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.2240. Min Act: -0.0001

Data Index: 1445923 (Python Code)

Max Activating Token Index: 715

Text #1

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.1254. Min Act: -0.0001

Data Index: 1439742 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.1188. Min Act: -0.0001

Data Index: 1451185 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.1514. Min Act: -0.0001

Data Index: 119688 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.1708. Min Act: -0.0001

Data Index: 23479 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.0926. Min Act: -0.0001

Data Index: 51452 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.1791. Min Act: -0.0000

Data Index: 1308148 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1327960 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.0250. Min Act: -0.0001

Data Index: 1462123 (Python Code)

Max Activating Token Index: 958

Text #9

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1224755 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.0202. Min Act: -0.0001

Data Index: 1596523 (Python Code)

Max Activating Token Index: 839

Text #11

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.0494. Min Act: -0.0000

Data Index: 538866 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.2240. Min Range: -1.2240

Max Act: 0.9713. Min Act: -0.0000

Data Index: 506728 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 1.2240. Min Range: -1.2240

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1342484 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 1.2240. Min Range: -1.2240

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1100443 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.2240. Min Range: -1.2240

Max Act: 0.9812. Min Act: -0.0000

Data Index: 733915 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 1.2240. Min Range: -1.2240

Max Act: 0.9599. Min Act: -0.0000

Data Index: 232293 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.2240. Min Range: -1.2240

Max Act: 0.9252. Min Act: -0.0000

Data Index: 428992 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.2240. Min Range: -1.2240

Max Act: 0.9222. Min Act: -0.0001

Data Index: 936520 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.2240. Min Range: -1.2240

Max Act: 0.9219. Min Act: -0.0000

Data Index: 147867 (C4 (Web Text))

Max Activating Token Index: 919