Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1233 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0003

Data Index: 345856 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0615. Min Act: -0.0003

Data Index: 433233 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0625. Min Act: -0.0003

Data Index: 467011 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1293952 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0554. Min Act: -0.0003

Data Index: 267462 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1064063 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0524. Min Act: -0.0003

Data Index: 792379 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0532. Min Act: -0.0003

Data Index: 497128 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1154462 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0465. Min Act: -0.0003

Data Index: 792323 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0449. Min Act: -0.0003

Data Index: 160235 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0507. Min Act: -0.0003

Data Index: 968509 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0491. Min Act: -0.0003

Data Index: 762440 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0495. Min Act: -0.0003

Data Index: 406367 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1190448 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0447. Min Act: -0.0003

Data Index: 350058 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1204311 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0459. Min Act: -0.0003

Data Index: 152892 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1355801 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0458. Min Act: -0.0003

Data Index: 832140 (C4 (Web Text))

Max Activating Token Index: 629