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

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

Neuron 616 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0486. Min Act: -0.0003

Data Index: 283673 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1017002 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0487. Min Act: -0.0003

Data Index: 76668 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0438. Min Act: -0.0003

Data Index: 324145 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0429. Min Act: -0.0002

Data Index: 823412 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0401. Min Act: -0.0002

Data Index: 988273 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1113464 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1272894 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0402. Min Act: -0.0002

Data Index: 951678 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0388. Min Act: -0.0003

Data Index: 884873 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0383. Min Act: -0.0002

Data Index: 161300 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0395. Min Act: -0.0003

Data Index: 329277 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0408. Min Act: -0.0003

Data Index: 608901 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0385. Min Act: -0.0003

Data Index: 380037 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1120547 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0377. Min Act: -0.0003

Data Index: 912736 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1352047 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0367. Min Act: -0.0003

Data Index: 411540 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0370. Min Act: -0.0003

Data Index: 58594 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.0510. Min Range: -0.0510

Max Act: 0.0366. Min Act: -0.0003

Data Index: 559268 (C4 (Web Text))

Max Activating Token Index: 724