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

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

Neuron 2977 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: 0.4532. Min Range: -0.4532

Max Act: 0.4532. Min Act: -0.0001

Data Index: 1046362 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.4110. Min Act: -0.0001

Data Index: 569703 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3775. Min Act: -0.0001

Data Index: 370706 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3802. Min Act: -0.0001

Data Index: 199659 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3425. Min Act: -0.0001

Data Index: 306151 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3438. Min Act: -0.0001

Data Index: 591550 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3316. Min Act: -0.0001

Data Index: 1077495 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3697. Min Act: -0.0001

Data Index: 730767 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3408. Min Act: -0.0001

Data Index: 180512 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1280800 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3126. Min Act: -0.0000

Data Index: 722833 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1165415 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1335059 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3221. Min Act: -0.0001

Data Index: 80191 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3373. Min Act: -0.0001

Data Index: 778173 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3192. Min Act: -0.0001

Data Index: 949958 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.2918. Min Act: -0.0000

Data Index: 223463 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3147. Min Act: -0.0001

Data Index: 57676 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3000. Min Act: -0.0001

Data Index: 192396 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.2968. Min Act: -0.0001

Data Index: 997739 (C4 (Web Text))

Max Activating Token Index: 195