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

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

Neuron 3695 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0392. Min Act: -0.0000

Data Index: 1484238 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0404. Min Act: -0.0000

Data Index: 1157644 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0000

Data Index: 920002 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0389. Min Act: -0.0000

Data Index: 684098 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0391. Min Act: -0.0000

Data Index: 10641 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0352. Min Act: -0.0000

Data Index: 182419 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1345236 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0358. Min Act: -0.0000

Data Index: 375119 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0358. Min Act: -0.0000

Data Index: 545954 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1166254 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0338. Min Act: -0.0000

Data Index: 106894 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1066360 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0374. Min Act: -0.0000

Data Index: 807007 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0372. Min Act: -0.0000

Data Index: 814676 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1349758 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0340. Min Act: -0.0000

Data Index: 257076 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0367. Min Act: -0.0000

Data Index: 814967 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0331. Min Act: -0.0000

Data Index: 1376072 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0331. Min Act: -0.0000

Data Index: 488270 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1513868 (Python Code)

Max Activating Token Index: 212