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

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

Neuron 950 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0002

Data Index: 734111 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0480. Min Act: -0.0003

Data Index: 846168 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0475. Min Act: -0.0003

Data Index: 432211 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0458. Min Act: -0.0002

Data Index: 652637 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0424. Min Act: -0.0003

Data Index: 816772 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0387. Min Act: -0.0003

Data Index: 141619 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1135035 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0392. Min Act: -0.0003

Data Index: 671376 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1305759 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1231056 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1328957 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0334. Min Act: -0.0003

Data Index: 666783 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0342. Min Act: -0.0003

Data Index: 186850 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1046782 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0326. Min Act: -0.0003

Data Index: 461699 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0323. Min Act: -0.0002

Data Index: 432442 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0322. Min Act: -0.0003

Data Index: 485299 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0310. Min Act: -0.0003

Data Index: 371635 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1147974 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0303. Min Act: -0.0002

Data Index: 31761 (C4 (Web Text))

Max Activating Token Index: 543