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

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

Neuron 1222 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: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0004

Data Index: 693625 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0655. Min Act: -0.0003

Data Index: 273680 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1224020 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1093740 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0531. Min Act: -0.0003

Data Index: 128247 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0542. Min Act: -0.0003

Data Index: 32725 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0528. Min Act: -0.0003

Data Index: 39898 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0546. Min Act: -0.0003

Data Index: 304294 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0546. Min Act: -0.0004

Data Index: 780910 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0526. Min Act: -0.0003

Data Index: 355904 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0510. Min Act: -0.0004

Data Index: 442328 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1129676 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0507. Min Act: -0.0003

Data Index: 386141 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1249693 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0487. Min Act: -0.0003

Data Index: 324573 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0506. Min Act: -0.0003

Data Index: 653712 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0513. Min Act: -0.0003

Data Index: 390263 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0497. Min Act: -0.0003

Data Index: 321448 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0515. Min Act: -0.0003

Data Index: 783769 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0487. Min Act: -0.0003

Data Index: 171431 (C4 (Web Text))

Max Activating Token Index: 415