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

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

Neuron 2854 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6860. Min Act: -0.0001

Data Index: 822828 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6353. Min Act: -0.0001

Data Index: 980076 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1271215 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5617. Min Act: -0.0001

Data Index: 546572 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5360. Min Act: -0.0001

Data Index: 1277922 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4974. Min Act: -0.0001

Data Index: 396325 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5048. Min Act: -0.0001

Data Index: 878351 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5090. Min Act: -0.0001

Data Index: 192663 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4886. Min Act: -0.0001

Data Index: 1074542 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5021. Min Act: -0.0001

Data Index: 551312 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4745. Min Act: -0.0001

Data Index: 1125322 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4709. Min Act: -0.0001

Data Index: 749516 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4655. Min Act: -0.0001

Data Index: 424104 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4733. Min Act: -0.0001

Data Index: 510810 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4549. Min Act: -0.0001

Data Index: 1168326 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4528. Min Act: -0.0001

Data Index: 453970 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4288. Min Act: -0.0001

Data Index: 666725 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4459. Min Act: -0.0001

Data Index: 1260107 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4493. Min Act: -0.0001

Data Index: 1278321 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.4340. Min Act: -0.0001

Data Index: 52017 (C4 (Web Text))

Max Activating Token Index: 509