Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1729 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0005

Data Index: 738180 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0588. Min Act: -0.0005

Data Index: 650537 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0514. Min Act: -0.0005

Data Index: 1011706 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0481. Min Act: -0.0005

Data Index: 92045 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0442. Min Act: -0.0005

Data Index: 1615417 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0458. Min Act: -0.0005

Data Index: 1432917 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0474. Min Act: -0.0005

Data Index: 262507 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0446. Min Act: -0.0005

Data Index: 569329 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0468. Min Act: -0.0005

Data Index: 1273523 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0483. Min Act: -0.0005

Data Index: 498149 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0464. Min Act: -0.0005

Data Index: 1445501 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0448. Min Act: -0.0005

Data Index: 719311 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0439. Min Act: -0.0005

Data Index: 496366 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0473. Min Act: -0.0005

Data Index: 997648 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0436. Min Act: -0.0005

Data Index: 1011526 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0443. Min Act: -0.0005

Data Index: 382435 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0434. Min Act: -0.0005

Data Index: 1125306 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0461. Min Act: -0.0005

Data Index: 5810 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0429. Min Act: -0.0005

Data Index: 1116827 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0481. Min Act: -0.0005

Data Index: 767558 (C4 (Web Text))

Max Activating Token Index: 410