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

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

Neuron 3208 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: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0003

Data Index: 861962 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0557. Min Act: -0.0002

Data Index: 381464 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0610. Min Act: -0.0002

Data Index: 934308 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0585. Min Act: -0.0003

Data Index: 588482 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1246276 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0541. Min Act: -0.0003

Data Index: 884360 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0512. Min Act: -0.0003

Data Index: 458491 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0529. Min Act: -0.0003

Data Index: 354169 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0515. Min Act: -0.0003

Data Index: 291388 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1108549 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0498. Min Act: -0.0003

Data Index: 396329 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1240298 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0489. Min Act: -0.0003

Data Index: 86195 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1197093 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0492. Min Act: -0.0003

Data Index: 436382 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0470. Min Act: -0.0003

Data Index: 154570 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1256866 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0457. Min Act: -0.0003

Data Index: 927277 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0448. Min Act: -0.0003

Data Index: 604509 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0430. Min Act: -0.0003

Data Index: 385387 (C4 (Web Text))

Max Activating Token Index: 279