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

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

Neuron 2416 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: 3.0498. Min Range: -3.0498

Max Act: 3.0498. Min Act: -0.0000

Data Index: 344144 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.6279. Min Act: -0.0000

Data Index: 249528 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.6176. Min Act: -0.0000

Data Index: 1092023 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.7356. Min Act: -0.0000

Data Index: 820936 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.5312. Min Act: -0.0000

Data Index: 1349344 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.4925. Min Act: -0.0000

Data Index: 354889 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.5892. Min Act: -0.0000

Data Index: 717915 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.2120. Min Act: -0.0000

Data Index: 914999 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.4343. Min Act: -0.0000

Data Index: 285906 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.1868. Min Act: -0.0000

Data Index: 57943 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.3121. Min Act: -0.0000

Data Index: 209578 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.2683. Min Act: -0.0000

Data Index: 1218849 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.2415. Min Act: -0.0000

Data Index: 789498 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.2375. Min Act: -0.0000

Data Index: 599840 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.1345. Min Act: -0.0000

Data Index: 354056 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.1726. Min Act: -0.0000

Data Index: 737235 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.1584. Min Act: -0.0000

Data Index: 836516 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.0275. Min Act: -0.0000

Data Index: 564319 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.1004. Min Act: -0.0000

Data Index: 681566 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 3.0498. Min Range: -3.0498

Max Act: 1.9647. Min Act: -0.0000

Data Index: 880961 (C4 (Web Text))

Max Activating Token Index: 1003