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

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

Neuron 744 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0063. Min Range: -1.0063

Max Act: 1.0063. Min Act: -0.0000

Data Index: 110966 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1157691 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1035062 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8983. Min Act: -0.0000

Data Index: 707455 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.9194. Min Act: -0.0000

Data Index: 34272 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1216708 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8727. Min Act: -0.0000

Data Index: 342894 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8659. Min Act: -0.0000

Data Index: 398065 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1295972 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8817. Min Act: -0.0000

Data Index: 237204 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1161941 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8410. Min Act: -0.0000

Data Index: 647677 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8421. Min Act: -0.0000

Data Index: 758728 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8376. Min Act: -0.0000

Data Index: 51166 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8305. Min Act: -0.0000

Data Index: 980916 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8310. Min Act: -0.0000

Data Index: 872571 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8578. Min Act: -0.0000

Data Index: 957876 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.8230. Min Act: -0.0000

Data Index: 15927 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.7978. Min Act: -0.0000

Data Index: 957188 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.0063. Min Range: -1.0063

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1105492 (C4 (Web Text))

Max Activating Token Index: 645