Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.5894. Min Act: -0.0000

Data Index: 1225796 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.3196. Min Act: -0.0000

Data Index: 792072 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.2087. Min Act: -0.0001

Data Index: 1075829 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0842. Min Act: -0.0001

Data Index: 1109664 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1329575 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1190. Min Act: -0.0001

Data Index: 403778 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0439. Min Act: -0.0001

Data Index: 1279917 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1434. Min Act: -0.0001

Data Index: 286416 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.1465. Min Act: -0.0001

Data Index: 719540 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0918. Min Act: -0.0001

Data Index: 883567 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.5894. Min Range: -1.5894

Max Act: 0.9431. Min Act: -0.0001

Data Index: 1358846 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0056. Min Act: -0.0001

Data Index: 632882 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0028. Min Act: -0.0001

Data Index: 675299 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0207. Min Act: -0.0001

Data Index: 236744 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.5894. Min Range: -1.5894

Max Act: 0.9598. Min Act: -0.0000

Data Index: 253825 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 1.5894. Min Range: -1.5894

Max Act: 0.9732. Min Act: -0.0001

Data Index: 64309 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.5894. Min Range: -1.5894

Max Act: 0.9031. Min Act: -0.0001

Data Index: 512812 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 1.5894. Min Range: -1.5894

Max Act: 0.9165. Min Act: -0.0000

Data Index: 693796 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.5894. Min Range: -1.5894

Max Act: 0.8854. Min Act: -0.0000

Data Index: 492418 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 1.5894. Min Range: -1.5894

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1138427 (C4 (Web Text))

Max Activating Token Index: 258