Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1428 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0001

Data Index: 809166 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0495. Min Act: -0.0000

Data Index: 929749 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1225898 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1311524 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0452. Min Act: -0.0000

Data Index: 1058085 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0474. Min Act: -0.0000

Data Index: 120241 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0388. Min Act: -0.0000

Data Index: 649171 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1283492 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0368. Min Act: -0.0000

Data Index: 193232 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0379. Min Act: -0.0000

Data Index: 115541 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0359. Min Act: -0.0000

Data Index: 193158 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0384. Min Act: -0.0000

Data Index: 857825 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0351. Min Act: -0.0000

Data Index: 616661 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0358. Min Act: -0.0000

Data Index: 226713 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0362. Min Act: -0.0000

Data Index: 130707 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0340. Min Act: -0.0000

Data Index: 155344 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1140464 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0344. Min Act: -0.0000

Data Index: 501026 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0346. Min Act: -0.0000

Data Index: 43587 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0329. Min Act: -0.0000

Data Index: 641254 (C4 (Web Text))

Max Activating Token Index: 576