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

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

Neuron 1150 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: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0002

Data Index: 880669 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1244152 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0361. Min Act: -0.0002

Data Index: 547423 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1096777 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0357. Min Act: -0.0002

Data Index: 23140 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0361. Min Act: -0.0001

Data Index: 741091 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0348. Min Act: -0.0002

Data Index: 581758 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0335. Min Act: -0.0002

Data Index: 484231 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1094060 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1066978 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0345. Min Act: -0.0002

Data Index: 196300 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0353. Min Act: -0.0002

Data Index: 971267 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0333. Min Act: -0.0002

Data Index: 368736 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0340. Min Act: -0.0002

Data Index: 637492 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0334. Min Act: -0.0002

Data Index: 373361 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0340. Min Act: -0.0002

Data Index: 484612 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0331. Min Act: -0.0002

Data Index: 556642 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0334. Min Act: -0.0002

Data Index: 702027 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1071511 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1297704 (C4 (Web Text))

Max Activating Token Index: 828