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

Dataset: The Pile

Neuron 4250 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2395. Min Range: -5.2395

Max Act: 5.2395. Min Act: -0.0000

Data Index: 1207610 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.3912. Min Act: -0.0000

Data Index: 689097 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.2323. Min Act: -0.0000

Data Index: 1624053 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.5964. Min Act: -0.0000

Data Index: 1537564 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.3227. Min Act: -0.0000

Data Index: 335084 (The Pile)

Max Activating Token Index: 760

Text #5

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.1299. Min Act: -0.0000

Data Index: 334564 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.2612. Min Act: -0.0000

Data Index: 1086126 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.2023. Min Act: -0.0000

Data Index: 577700 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 5.2395. Min Range: -5.2395

Max Act: 3.9433. Min Act: -0.0000

Data Index: 1276528 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.2500. Min Act: -0.0000

Data Index: 1470730 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.1083. Min Act: -0.0000

Data Index: 1150795 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 5.2395. Min Range: -5.2395

Max Act: 3.8915. Min Act: -0.0000

Data Index: 1437038 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.0667. Min Act: -0.0000

Data Index: 477582 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.2845. Min Act: -0.0000

Data Index: 50436 (The Pile)

Max Activating Token Index: 232

Text #14

Max Range: 5.2395. Min Range: -5.2395

Max Act: 3.6468. Min Act: -0.0000

Data Index: 942151 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 5.2395. Min Range: -5.2395

Max Act: 3.9774. Min Act: -0.0000

Data Index: 530071 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 5.2395. Min Range: -5.2395

Max Act: 3.1824. Min Act: -0.0000

Data Index: 1897132 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 5.2395. Min Range: -5.2395

Max Act: 4.2405. Min Act: -0.0000

Data Index: 623404 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 5.2395. Min Range: -5.2395

Max Act: 3.4295. Min Act: -0.0000

Data Index: 1742308 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 5.2395. Min Range: -5.2395

Max Act: 3.7278. Min Act: -0.0000

Data Index: 381828 (The Pile)

Max Activating Token Index: 30