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

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

Neuron 5092 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6481. Min Range: -3.6481

Max Act: 3.6481. Min Act: -0.0000

Data Index: 627819 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 3.6481. Min Range: -3.6481

Max Act: 3.3503. Min Act: -0.0000

Data Index: 1300195 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 3.6481. Min Range: -3.6481

Max Act: 3.3303. Min Act: -0.0000

Data Index: 1143092 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.9429. Min Act: -0.0000

Data Index: 563670 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 3.6481. Min Range: -3.6481

Max Act: 3.0785. Min Act: -0.0000

Data Index: 1131833 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 3.6481. Min Range: -3.6481

Max Act: 3.0311. Min Act: -0.0000

Data Index: 92919 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.8846. Min Act: -0.0000

Data Index: 885204 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.7306. Min Act: -0.0000

Data Index: 1086244 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.8030. Min Act: -0.0000

Data Index: 135425 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.6636. Min Act: -0.0000

Data Index: 1227856 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.7577. Min Act: -0.0000

Data Index: 740259 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.7144. Min Act: -0.0000

Data Index: 1087201 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.5270. Min Act: -0.0000

Data Index: 987222 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.5343. Min Act: -0.0000

Data Index: 980375 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.5275. Min Act: -0.0000

Data Index: 386533 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.6141. Min Act: -0.0000

Data Index: 1185991 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.4836. Min Act: -0.0000

Data Index: 166957 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.4451. Min Act: -0.0000

Data Index: 1032981 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.5713. Min Act: -0.0000

Data Index: 1073431 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 3.6481. Min Range: -3.6481

Max Act: 2.3884. Min Act: -0.0000

Data Index: 605473 (C4 (Web Text))

Max Activating Token Index: 503