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

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

Neuron 3769 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.6061. Min Act: -0.0001

Data Index: 415485 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5899. Min Act: -0.0001

Data Index: 860558 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5478. Min Act: -0.0001

Data Index: 214809 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5213. Min Act: -0.0001

Data Index: 234172 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5548. Min Act: -0.0001

Data Index: 889017 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5118. Min Act: -0.0001

Data Index: 765450 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5191. Min Act: -0.0001

Data Index: 347756 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5352. Min Act: -0.0001

Data Index: 39578 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5211. Min Act: -0.0001

Data Index: 1291783 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5116. Min Act: -0.0001

Data Index: 168980 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5115. Min Act: -0.0001

Data Index: 802500 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5217. Min Act: -0.0001

Data Index: 71834 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5211. Min Act: -0.0001

Data Index: 1131387 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1259590 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5333. Min Act: -0.0001

Data Index: 167204 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5118. Min Act: -0.0001

Data Index: 1354656 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4877. Min Act: -0.0001

Data Index: 567152 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4631. Min Act: -0.0001

Data Index: 1308094 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.4961. Min Act: -0.0001

Data Index: 489639 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.6061. Min Range: -0.6061

Max Act: 0.5058. Min Act: -0.0001

Data Index: 385795 (C4 (Web Text))

Max Activating Token Index: 832