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

Dataset: The Pile

Neuron 1964 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0842. Min Range: -1.0842

Max Act: 1.0842. Min Act: -0.0000

Data Index: 441868 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9146. Min Act: -0.0000

Data Index: 264857 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8589. Min Act: -0.0000

Data Index: 681014 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9611. Min Act: -0.0000

Data Index: 23915 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9427. Min Act: -0.0000

Data Index: 642024 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1338648 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9226. Min Act: -0.0000

Data Index: 655478 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1535075 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1848307 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1331083 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1066537 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1818137 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8038. Min Act: -0.0000

Data Index: 472210 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8423. Min Act: -0.0000

Data Index: 207365 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1647587 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8153. Min Act: -0.0000

Data Index: 482343 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8207. Min Act: -0.0000

Data Index: 658854 (The Pile)

Max Activating Token Index: 274

Text #17

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8238. Min Act: -0.0000

Data Index: 14165 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8420. Min Act: -0.0000

Data Index: 182729 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1378076 (The Pile)

Max Activating Token Index: 771