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

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

Neuron 17 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3831. Min Act: 0.0000

Data Index: 746066 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1006128 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3379. Min Act: -0.0000

Data Index: 807784 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3329. Min Act: -0.0000

Data Index: 61579 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3527. Min Act: -0.0000

Data Index: 752518 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1187695 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3448. Min Act: -0.0000

Data Index: 762248 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3259. Min Act: -0.0000

Data Index: 239110 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3408. Min Act: -0.0000

Data Index: 87229 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1091973 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3244. Min Act: -0.0000

Data Index: 984035 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3287. Min Act: -0.0000

Data Index: 870289 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1046686 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1120246 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1028671 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3255. Min Act: -0.0000

Data Index: 49665 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1262798 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3201. Min Act: -0.0000

Data Index: 831992 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1239914 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3225. Min Act: -0.0000

Data Index: 588343 (C4 (Web Text))

Max Activating Token Index: 392