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

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

Neuron 1050 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: 0.0615. Min Range: -0.0615

Max Act: 0.0583. Min Act: -0.0003

Data Index: 490814 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0003

Data Index: 235354 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0540. Min Act: -0.0003

Data Index: 532494 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0542. Min Act: -0.0003

Data Index: 468450 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1127132 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0547. Min Act: -0.0003

Data Index: 497565 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1133312 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0506. Min Act: -0.0003

Data Index: 561747 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0501. Min Act: -0.0003

Data Index: 803785 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1062393 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1291578 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0487. Min Act: -0.0003

Data Index: 241981 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0490. Min Act: -0.0003

Data Index: 563503 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0494. Min Act: -0.0003

Data Index: 477708 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0480. Min Act: -0.0003

Data Index: 947427 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0491. Min Act: -0.0003

Data Index: 443177 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0464. Min Act: -0.0003

Data Index: 317456 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0461. Min Act: -0.0003

Data Index: 938128 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0483. Min Act: -0.0004

Data Index: 143757 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1000807 (C4 (Web Text))

Max Activating Token Index: 598