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

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

Neuron 661 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: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0005

Data Index: 1241658 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0451. Min Act: -0.0005

Data Index: 195113 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0465. Min Act: -0.0005

Data Index: 905431 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0420. Min Act: -0.0005

Data Index: 1116031 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0421. Min Act: -0.0005

Data Index: 1159813 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0410. Min Act: -0.0005

Data Index: 484817 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0414. Min Act: -0.0005

Data Index: 790288 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0420. Min Act: -0.0005

Data Index: 7669 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0412. Min Act: -0.0005

Data Index: 88181 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0411. Min Act: -0.0005

Data Index: 291126 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0401. Min Act: -0.0005

Data Index: 694469 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0398. Min Act: -0.0005

Data Index: 5270 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0399. Min Act: -0.0005

Data Index: 896566 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0392. Min Act: -0.0005

Data Index: 483591 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0375. Min Act: -0.0005

Data Index: 785002 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0399. Min Act: -0.0005

Data Index: 1118522 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0389. Min Act: -0.0005

Data Index: 219339 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0393. Min Act: -0.0005

Data Index: 1093473 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0384. Min Act: -0.0005

Data Index: 1068278 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0370. Min Act: -0.0005

Data Index: 877766 (C4 (Web Text))

Max Activating Token Index: 880