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

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

Neuron 302 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: 938610 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0545. Min Act: -0.0005

Data Index: 64052 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0512. Min Act: -0.0005

Data Index: 1162879 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0509. Min Act: -0.0005

Data Index: 1118122 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0527. Min Act: -0.0004

Data Index: 477278 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0514. Min Act: -0.0005

Data Index: 45604 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0513. Min Act: -0.0004

Data Index: 811063 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0503. Min Act: -0.0005

Data Index: 1116735 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0473. Min Act: -0.0005

Data Index: 913899 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0468. Min Act: -0.0004

Data Index: 266633 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0492. Min Act: -0.0005

Data Index: 381982 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0477. Min Act: -0.0004

Data Index: 1042778 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0473. Min Act: -0.0005

Data Index: 916206 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0472. Min Act: -0.0005

Data Index: 1336534 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0449. Min Act: -0.0004

Data Index: 1270528 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0471. Min Act: -0.0005

Data Index: 800537 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0458. Min Act: -0.0005

Data Index: 747108 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0441. Min Act: -0.0004

Data Index: 595710 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0451. Min Act: -0.0005

Data Index: 1283445 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0465. Min Act: -0.0005

Data Index: 18253 (C4 (Web Text))

Max Activating Token Index: 145