Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1154570 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0632. Min Act: -0.0000

Data Index: 429508 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0573. Min Act: -0.0000

Data Index: 574984 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1317498 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1175981 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0512. Min Act: -0.0000

Data Index: 765415 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1641246 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0513. Min Act: -0.0000

Data Index: 615572 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0572. Min Act: -0.0000

Data Index: 378380 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0492. Min Act: -0.0000

Data Index: 901976 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1353481 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0518. Min Act: -0.0000

Data Index: 607889 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0479. Min Act: -0.0000

Data Index: 2960 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0457. Min Act: -0.0000

Data Index: 861693 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0465. Min Act: -0.0000

Data Index: 344149 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1360135 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0446. Min Act: -0.0000

Data Index: 604309 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1205908 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0460. Min Act: -0.0000

Data Index: 195615 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0443. Min Act: -0.0000

Data Index: 864086 (C4 (Web Text))

Max Activating Token Index: 620