Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3730 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.6957. Min Act: -0.0000

Data Index: 119542 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.6267. Min Act: -0.0000

Data Index: 173428 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5592. Min Act: -0.0001

Data Index: 819173 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.6067. Min Act: -0.0000

Data Index: 250258 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5806. Min Act: -0.0000

Data Index: 732869 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5422. Min Act: -0.0001

Data Index: 794660 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5411. Min Act: -0.0000

Data Index: 420854 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5730. Min Act: -0.0001

Data Index: 730186 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5134. Min Act: -0.0001

Data Index: 321663 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1301016 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1349366 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5188. Min Act: -0.0001

Data Index: 41414 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5293. Min Act: -0.0001

Data Index: 82547 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5306. Min Act: -0.0000

Data Index: 293475 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1151202 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5095. Min Act: -0.0000

Data Index: 8794 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5176. Min Act: -0.0000

Data Index: 301528 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5080. Min Act: -0.0000

Data Index: 390642 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.4473. Min Act: -0.0001

Data Index: 58282 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.6957. Min Range: -0.6957

Max Act: 0.5403. Min Act: -0.0000

Data Index: 907216 (C4 (Web Text))

Max Activating Token Index: 956