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

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

Neuron 3000 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: 0.4427. Min Range: -0.4427

Max Act: 0.4427. Min Act: 0.0000

Data Index: 478527 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3587. Min Act: -0.0000

Data Index: 282940 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1073017 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3321. Min Act: -0.0000

Data Index: 233832 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1342693 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.3035. Min Act: -0.0000

Data Index: 822467 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2806. Min Act: -0.0000

Data Index: 595710 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2933. Min Act: -0.0000

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2841. Min Act: -0.0001

Data Index: 855392 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2894. Min Act: -0.0001

Data Index: 622118 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2798. Min Act: -0.0000

Data Index: 635840 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2633. Min Act: -0.0000

Data Index: 284497 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2635. Min Act: -0.0000

Data Index: 461441 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1346934 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2474. Min Act: -0.0001

Data Index: 439076 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1110268 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2438. Min Act: -0.0000

Data Index: 64003 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2374. Min Act: -0.0000

Data Index: 666618 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.4427. Min Range: -0.4427

Max Act: 0.2126. Min Act: -0.0000

Data Index: 34159 (C4 (Web Text))

Max Activating Token Index: 330