Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1475 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.2579. Min Act: -0.0000

Data Index: 257156 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.2006. Min Act: -0.0000

Data Index: 193142 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1652. Min Act: -0.0000

Data Index: 984845 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1332. Min Act: -0.0000

Data Index: 1202946 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1646. Min Act: -0.0000

Data Index: 655469 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1488. Min Act: -0.0000

Data Index: 790009 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0667. Min Act: -0.0000

Data Index: 573299 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1671. Min Act: -0.0000

Data Index: 418845 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1225. Min Act: -0.0000

Data Index: 516516 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1223. Min Act: -0.0000

Data Index: 21040 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0382. Min Act: -0.0000

Data Index: 139001 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0786. Min Act: -0.0000

Data Index: 432778 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1155644 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.1377. Min Act: -0.0000

Data Index: 42752 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1210301 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0570. Min Act: -0.0000

Data Index: 791871 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0861. Min Act: -0.0000

Data Index: 589659 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1141195 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0745. Min Act: -0.0000

Data Index: 225912 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 1.2579. Min Range: -1.2579

Max Act: 1.0578. Min Act: -0.0000

Data Index: 637470 (C4 (Web Text))

Max Activating Token Index: 316