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

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

Neuron 648 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0497. Min Act: -0.0003

Data Index: 7866 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1048362 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0478. Min Act: -0.0002

Data Index: 812038 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0475. Min Act: -0.0002

Data Index: 434836 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0481. Min Act: -0.0002

Data Index: 782504 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0468. Min Act: -0.0002

Data Index: 266301 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1208998 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1169477 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0458. Min Act: -0.0003

Data Index: 429250 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0452. Min Act: -0.0003

Data Index: 627024 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0445. Min Act: -0.0002

Data Index: 497873 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0452. Min Act: -0.0002

Data Index: 645814 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1062418 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0453. Min Act: -0.0002

Data Index: 839087 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0444. Min Act: -0.0002

Data Index: 619261 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0438. Min Act: -0.0002

Data Index: 84371 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0437. Min Act: -0.0002

Data Index: 920225 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1142277 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1098888 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0443. Min Act: -0.0002

Data Index: 928469 (C4 (Web Text))

Max Activating Token Index: 661