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

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

Neuron 2682 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0566. Min Act: -0.0002

Data Index: 921905 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0554. Min Act: -0.0002

Data Index: 862489 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0569. Min Act: -0.0002

Data Index: 976069 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0566. Min Act: -0.0002

Data Index: 172961 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0517. Min Act: -0.0002

Data Index: 708555 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0475. Min Act: -0.0002

Data Index: 709399 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0487. Min Act: -0.0002

Data Index: 745351 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1268172 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1211283 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0539. Min Act: -0.0002

Data Index: 329583 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0449. Min Act: -0.0002

Data Index: 844813 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0478. Min Act: -0.0002

Data Index: 246363 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0395. Min Act: -0.0002

Data Index: 362285 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1185068 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0405. Min Act: -0.0002

Data Index: 343953 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1187398 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0433. Min Act: -0.0002

Data Index: 904431 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0354. Min Act: -0.0002

Data Index: 322511 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1017749 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.0569. Min Range: -0.0569

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1332603 (C4 (Web Text))

Max Activating Token Index: 968