Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2157 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1400659 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0633. Min Act: -0.0000

Data Index: 626806 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1568551 (Python Code)

Max Activating Token Index: 251

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0595. Min Act: -0.0000

Data Index: 537288 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1132244 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1163365 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0515. Min Act: -0.0000

Data Index: 348547 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0564. Min Act: -0.0000

Data Index: 497249 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0526. Min Act: -0.0000

Data Index: 700428 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0511. Min Act: -0.0000

Data Index: 84945 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0515. Min Act: -0.0000

Data Index: 82669 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0497. Min Act: -0.0000

Data Index: 723892 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1452327 (Python Code)

Max Activating Token Index: 154

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0469. Min Act: -0.0000

Data Index: 737408 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1552283 (Python Code)

Max Activating Token Index: 702

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0470. Min Act: -0.0000

Data Index: 881252 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0469. Min Act: -0.0000

Data Index: 120638 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0489. Min Act: -0.0000

Data Index: 815334 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0477. Min Act: -0.0000

Data Index: 466328 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1615041 (Python Code)

Max Activating Token Index: 738