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

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

Neuron 5093 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0559. Min Act: -0.0000

Data Index: 742216 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0543. Min Act: -0.0000

Data Index: 873645 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1249479 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0454. Min Act: -0.0001

Data Index: 757188 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1087482 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0412. Min Act: -0.0000

Data Index: 673956 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1072699 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0378. Min Act: -0.0001

Data Index: 314043 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0377. Min Act: -0.0000

Data Index: 464887 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1123100 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0385. Min Act: -0.0001

Data Index: 530522 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1270407 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0363. Min Act: -0.0001

Data Index: 823503 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0389. Min Act: -0.0001

Data Index: 261807 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0363. Min Act: -0.0000

Data Index: 364521 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0350. Min Act: -0.0000

Data Index: 376200 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1073104 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1207400 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0351. Min Act: -0.0001

Data Index: 960713 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0310. Min Act: -0.0000

Data Index: 26212 (C4 (Web Text))

Max Activating Token Index: 708