Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 154 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0474. Min Act: -0.0003

Data Index: 166138 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0003

Data Index: 214759 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0467. Min Act: -0.0003

Data Index: 605922 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0473. Min Act: -0.0003

Data Index: 249435 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0416. Min Act: -0.0003

Data Index: 792441 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0389. Min Act: -0.0003

Data Index: 910161 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0373. Min Act: -0.0003

Data Index: 498132 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1359197 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0363. Min Act: -0.0003

Data Index: 246636 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0354. Min Act: -0.0003

Data Index: 926779 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0384. Min Act: -0.0003

Data Index: 69209 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1049487 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0418. Min Act: -0.0003

Data Index: 618164 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0349. Min Act: -0.0003

Data Index: 665055 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0344. Min Act: -0.0003

Data Index: 571506 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0376. Min Act: -0.0003

Data Index: 275552 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0364. Min Act: -0.0003

Data Index: 231706 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0329. Min Act: -0.0003

Data Index: 636465 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0310. Min Act: -0.0003

Data Index: 365138 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0341. Min Act: -0.0003

Data Index: 410419 (C4 (Web Text))

Max Activating Token Index: 420