Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1510 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0003

Data Index: 143208 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1334049 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1224960 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1327343 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0409. Min Act: -0.0003

Data Index: 49300 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0407. Min Act: -0.0004

Data Index: 690648 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0404. Min Act: -0.0002

Data Index: 219384 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1202144 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0399. Min Act: -0.0003

Data Index: 600446 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0398. Min Act: -0.0003

Data Index: 899604 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1310390 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0390. Min Act: -0.0004

Data Index: 1077809 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0397. Min Act: -0.0003

Data Index: 781660 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0379. Min Act: -0.0003

Data Index: 978089 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0389. Min Act: -0.0003

Data Index: 345231 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0373. Min Act: -0.0003

Data Index: 181414 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0377. Min Act: -0.0004

Data Index: 1355945 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0378. Min Act: -0.0003

Data Index: 22346 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0368. Min Act: -0.0003

Data Index: 856738 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0360. Min Act: -0.0003

Data Index: 453784 (C4 (Web Text))

Max Activating Token Index: 665