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

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

Neuron 1949 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: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0003

Data Index: 689088 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0658. Min Act: -0.0003

Data Index: 120155 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0617. Min Act: -0.0003

Data Index: 267914 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0583. Min Act: -0.0003

Data Index: 321748 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0573. Min Act: -0.0003

Data Index: 564226 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1117987 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0562. Min Act: -0.0004

Data Index: 288317 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1043228 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0537. Min Act: -0.0003

Data Index: 497768 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0523. Min Act: -0.0003

Data Index: 788332 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0539. Min Act: -0.0003

Data Index: 783790 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0523. Min Act: -0.0003

Data Index: 503464 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0529. Min Act: -0.0003

Data Index: 441638 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0513. Min Act: -0.0003

Data Index: 323368 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0527. Min Act: -0.0003

Data Index: 633177 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1034471 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0502. Min Act: -0.0003

Data Index: 742290 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0519. Min Act: -0.0003

Data Index: 697752 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0488. Min Act: -0.0003

Data Index: 353517 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1289824 (C4 (Web Text))

Max Activating Token Index: 77