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

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

Neuron 372 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: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0003

Data Index: 693187 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0584. Min Act: -0.0003

Data Index: 455902 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0561. Min Act: -0.0003

Data Index: 131037 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0554. Min Act: -0.0003

Data Index: 874190 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0539. Min Act: -0.0003

Data Index: 924852 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1260681 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0525. Min Act: -0.0003

Data Index: 121741 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0531. Min Act: -0.0004

Data Index: 214207 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0514. Min Act: -0.0003

Data Index: 508325 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0504. Min Act: -0.0004

Data Index: 71954 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0504. Min Act: -0.0003

Data Index: 217381 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0518. Min Act: -0.0003

Data Index: 871625 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0482. Min Act: -0.0004

Data Index: 243543 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1083285 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0481. Min Act: -0.0003

Data Index: 505485 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0485. Min Act: -0.0003

Data Index: 346059 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0483. Min Act: -0.0003

Data Index: 661462 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0484. Min Act: -0.0003

Data Index: 427867 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1232597 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0470. Min Act: -0.0003

Data Index: 735663 (C4 (Web Text))

Max Activating Token Index: 459