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

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

Neuron 159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.4023. Min Act: -0.0000

Data Index: 741971 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1160651 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.3156. Min Act: -0.0000

Data Index: 414272 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1251520 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2887. Min Act: -0.0001

Data Index: 905210 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1237115 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2660. Min Act: -0.0000

Data Index: 963672 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2610. Min Act: -0.0000

Data Index: 577016 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2364. Min Act: -0.0000

Data Index: 971033 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2377. Min Act: -0.0001

Data Index: 290959 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2288. Min Act: -0.0000

Data Index: 214149 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2358. Min Act: -0.0000

Data Index: 645660 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2164. Min Act: -0.0001

Data Index: 346787 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2333. Min Act: -0.0000

Data Index: 721295 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2155. Min Act: -0.0000

Data Index: 535000 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2118. Min Act: -0.0000

Data Index: 772695 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2033. Min Act: -0.0001

Data Index: 960839 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1155135 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2098. Min Act: -0.0000

Data Index: 187005 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.4023. Min Range: -0.4023

Max Act: 0.2024. Min Act: -0.0001

Data Index: 219619 (C4 (Web Text))

Max Activating Token Index: 565