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

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

Neuron 616 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.8541. Min Act: -0.0001

Data Index: 1241571 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.7017. Min Act: -0.0001

Data Index: 803528 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6249. Min Act: -0.0001

Data Index: 271913 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.6329. Min Act: -0.0001

Data Index: 218928 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5611. Min Act: -0.0001

Data Index: 825835 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5323. Min Act: -0.0001

Data Index: 208032 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5539. Min Act: -0.0001

Data Index: 374758 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1243134 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5458. Min Act: -0.0001

Data Index: 1155187 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5262. Min Act: -0.0001

Data Index: 1142903 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5221. Min Act: -0.0001

Data Index: 29354 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5055. Min Act: -0.0001

Data Index: 224240 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5005. Min Act: -0.0001

Data Index: 365844 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5227. Min Act: -0.0001

Data Index: 1150373 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5815. Min Act: -0.0001

Data Index: 418532 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5230. Min Act: -0.0001

Data Index: 1062573 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5411. Min Act: -0.0001

Data Index: 1261151 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5201. Min Act: -0.0001

Data Index: 1230289 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5489. Min Act: -0.0001

Data Index: 879854 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.8541. Min Range: -0.8541

Max Act: 0.5207. Min Act: -0.0001

Data Index: 960703 (C4 (Web Text))

Max Activating Token Index: 660