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

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

Neuron 1626 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4351. Min Act: 0.0001

Data Index: 1233422 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4194. Min Act: -0.0000

Data Index: 42765 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4019. Min Act: -0.0000

Data Index: 946522 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3944. Min Act: -0.0000

Data Index: 184911 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3963. Min Act: -0.0000

Data Index: 975643 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3772. Min Act: -0.0000

Data Index: 744270 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3874. Min Act: 0.0000

Data Index: 450323 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3846. Min Act: -0.0000

Data Index: 650185 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3671. Min Act: -0.0000

Data Index: 129286 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3338. Min Act: -0.0000

Data Index: 630955 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3542. Min Act: -0.0000

Data Index: 520508 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3606. Min Act: -0.0000

Data Index: 586270 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3370. Min Act: -0.0000

Data Index: 458105 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3607. Min Act: -0.0000

Data Index: 130113 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1219603 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1181239 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3287. Min Act: -0.0000

Data Index: 86439 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3260. Min Act: -0.0000

Data Index: 356980 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3466. Min Act: -0.0000

Data Index: 884543 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3358. Min Act: -0.0000

Data Index: 180220 (C4 (Web Text))

Max Activating Token Index: 457