Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 862 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.3379. Min Act: -0.0001

Data Index: 390181 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2518. Min Act: -0.0001

Data Index: 419420 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2196. Min Act: -0.0001

Data Index: 870767 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2361. Min Act: -0.0001

Data Index: 159840 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2211. Min Act: -0.0001

Data Index: 539227 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2267. Min Act: -0.0001

Data Index: 141244 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2329. Min Act: -0.0001

Data Index: 797948 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2183. Min Act: -0.0001

Data Index: 568418 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2158. Min Act: -0.0001

Data Index: 759828 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2152. Min Act: -0.0001

Data Index: 1068938 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2040. Min Act: -0.0001

Data Index: 818923 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2038. Min Act: -0.0001

Data Index: 918093 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2010. Min Act: -0.0001

Data Index: 797435 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2126. Min Act: -0.0001

Data Index: 309572 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1240542 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1053562 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2029. Min Act: -0.0001

Data Index: 737719 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1058215 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2041. Min Act: -0.0001

Data Index: 701696 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.1903. Min Act: -0.0001

Data Index: 330420 (C4 (Web Text))

Max Activating Token Index: 815