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

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

Neuron 1332 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: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0003

Data Index: 98927 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0534. Min Act: -0.0004

Data Index: 962288 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0528. Min Act: -0.0004

Data Index: 973490 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0517. Min Act: -0.0002

Data Index: 18063 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1249936 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0519. Min Act: -0.0003

Data Index: 415026 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0524. Min Act: -0.0003

Data Index: 504957 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0509. Min Act: -0.0002

Data Index: 940466 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1204718 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0474. Min Act: -0.0002

Data Index: 651376 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1151707 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0483. Min Act: -0.0002

Data Index: 938209 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0465. Min Act: -0.0003

Data Index: 925789 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0462. Min Act: -0.0003

Data Index: 961312 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0471. Min Act: -0.0002

Data Index: 448478 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1179423 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0464. Min Act: -0.0003

Data Index: 877608 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0454. Min Act: -0.0003

Data Index: 637573 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0464. Min Act: -0.0003

Data Index: 933223 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0465. Min Act: -0.0003

Data Index: 582353 (C4 (Web Text))

Max Activating Token Index: 681