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

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

Neuron 338 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: 0.0587. Min Range: -0.0587

Max Act: 0.0587. Min Act: -0.0005

Data Index: 724138 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0580. Min Act: -0.0005

Data Index: 415269 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0540. Min Act: -0.0005

Data Index: 1339688 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0534. Min Act: -0.0005

Data Index: 1147330 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0517. Min Act: -0.0005

Data Index: 653251 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0515. Min Act: -0.0005

Data Index: 820936 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0535. Min Act: -0.0005

Data Index: 1348071 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0529. Min Act: -0.0005

Data Index: 441847 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0513. Min Act: -0.0005

Data Index: 1143608 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0503. Min Act: -0.0005

Data Index: 399322 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0484. Min Act: -0.0005

Data Index: 1130935 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0490. Min Act: -0.0005

Data Index: 142993 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0496. Min Act: -0.0005

Data Index: 886067 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0506. Min Act: -0.0005

Data Index: 854337 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0440. Min Act: -0.0005

Data Index: 962635 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0495. Min Act: -0.0005

Data Index: 1144344 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0474. Min Act: -0.0005

Data Index: 447010 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0523. Min Act: -0.0005

Data Index: 332060 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0469. Min Act: -0.0005

Data Index: 643580 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0509. Min Act: -0.0005

Data Index: 1144991 (C4 (Web Text))

Max Activating Token Index: 618