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

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

Neuron 3526 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1202270 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5658. Min Act: -0.0000

Data Index: 172709 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4600. Min Act: -0.0000

Data Index: 96622 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5533. Min Act: -0.0000

Data Index: 954823 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5295. Min Act: -0.0000

Data Index: 547170 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4995. Min Act: -0.0000

Data Index: 641151 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5033. Min Act: -0.0000

Data Index: 147372 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5302. Min Act: -0.0000

Data Index: 634391 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5014. Min Act: -0.0000

Data Index: 430219 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1309089 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4820. Min Act: -0.0000

Data Index: 604549 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1188845 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4744. Min Act: -0.0000

Data Index: 592638 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4652. Min Act: -0.0000

Data Index: 171628 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4522. Min Act: -0.0000

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4385. Min Act: -0.0000

Data Index: 438747 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4521. Min Act: -0.0000

Data Index: 103802 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4371. Min Act: -0.0000

Data Index: 89339 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1127399 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4901. Min Act: -0.0000

Data Index: 55102 (C4 (Web Text))

Max Activating Token Index: 610