Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0003

Data Index: 324408 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1228982 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0517. Min Act: -0.0003

Data Index: 588795 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0513. Min Act: -0.0003

Data Index: 4078 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0486. Min Act: -0.0003

Data Index: 72075 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0482. Min Act: -0.0002

Data Index: 804819 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0482. Min Act: -0.0003

Data Index: 908239 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0490. Min Act: -0.0002

Data Index: 471154 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0469. Min Act: -0.0003

Data Index: 688176 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0477. Min Act: -0.0003

Data Index: 791056 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1310364 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0462. Min Act: -0.0002

Data Index: 79564 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0464. Min Act: -0.0003

Data Index: 108046 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0453. Min Act: -0.0003

Data Index: 83041 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0446. Min Act: -0.0003

Data Index: 248023 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0461. Min Act: -0.0002

Data Index: 731395 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0449. Min Act: -0.0003

Data Index: 521642 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1215292 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1212092 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0448. Min Act: -0.0003

Data Index: 324575 (C4 (Web Text))

Max Activating Token Index: 862