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

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

Neuron 1788 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0006

Data Index: 513449 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0545. Min Act: -0.0006

Data Index: 86257 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0531. Min Act: -0.0006

Data Index: 683384 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0581. Min Act: -0.0006

Data Index: 527983 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0499. Min Act: -0.0006

Data Index: 934568 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0523. Min Act: -0.0006

Data Index: 379409 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0497. Min Act: -0.0006

Data Index: 206932 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0508. Min Act: -0.0006

Data Index: 1115596 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0485. Min Act: -0.0006

Data Index: 230146 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0504. Min Act: -0.0006

Data Index: 84331 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0469. Min Act: -0.0006

Data Index: 825374 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0474. Min Act: -0.0006

Data Index: 1270556 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0483. Min Act: -0.0006

Data Index: 1061113 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0495. Min Act: -0.0006

Data Index: 1059737 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0537. Min Act: -0.0006

Data Index: 54624 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0491. Min Act: -0.0006

Data Index: 909326 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0473. Min Act: -0.0006

Data Index: 1072776 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0471. Min Act: -0.0006

Data Index: 38977 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0517. Min Act: -0.0006

Data Index: 204613 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0422. Min Act: -0.0006

Data Index: 915030 (C4 (Web Text))

Max Activating Token Index: 975