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

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

Neuron 1698 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0513. Min Act: -0.0002

Data Index: 559332 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0457. Min Act: -0.0002

Data Index: 118002 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0459. Min Act: -0.0002

Data Index: 772355 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0453. Min Act: -0.0002

Data Index: 61554 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1267209 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0408. Min Act: -0.0002

Data Index: 107967 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0438. Min Act: -0.0002

Data Index: 370206 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0426. Min Act: -0.0002

Data Index: 340990 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0431. Min Act: -0.0002

Data Index: 823122 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1280062 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0399. Min Act: -0.0002

Data Index: 583730 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0393. Min Act: -0.0002

Data Index: 546825 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0407. Min Act: -0.0002

Data Index: 509506 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0385. Min Act: -0.0002

Data Index: 701132 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1126888 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0379. Min Act: -0.0002

Data Index: 538690 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1202576 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0382. Min Act: -0.0002

Data Index: 781841 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0389. Min Act: -0.0002

Data Index: 984002 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0387. Min Act: -0.0002

Data Index: 869221 (C4 (Web Text))

Max Activating Token Index: 987