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

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

Neuron 2111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2902. Min Act: -0.0000

Data Index: 80621 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2898. Min Act: -0.0001

Data Index: 1267912 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2887. Min Act: -0.0000

Data Index: 421418 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2718. Min Act: -0.0000

Data Index: 540114 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2488. Min Act: -0.0000

Data Index: 742753 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2422. Min Act: -0.0000

Data Index: 551795 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2682. Min Act: -0.0001

Data Index: 811168 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1013404 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2531. Min Act: -0.0000

Data Index: 260594 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2695. Min Act: -0.0000

Data Index: 50590 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2533. Min Act: -0.0000

Data Index: 78450 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1011167 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2581. Min Act: -0.0000

Data Index: 74864 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2316. Min Act: -0.0001

Data Index: 1054174 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2320. Min Act: -0.0000

Data Index: 384402 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2481. Min Act: -0.0000

Data Index: 484697 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2359. Min Act: -0.0000

Data Index: 49946 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2222. Min Act: -0.0000

Data Index: 560219 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2376. Min Act: -0.0000

Data Index: 285966 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1052248 (C4 (Web Text))

Max Activating Token Index: 756