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

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

Neuron 1888 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1731. Min Act: -0.0000

Data Index: 781760 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1580. Min Act: -0.0000

Data Index: 914814 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1006323 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1077598 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.1900. Min Act: -0.0001

Data Index: 801096 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0773. Min Act: -0.0001

Data Index: 345322 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1135192 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.1900. Min Range: -1.1900

Max Act: 1.0172. Min Act: -0.0000

Data Index: 469867 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.9089. Min Act: -0.0000

Data Index: 431273 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.8961. Min Act: -0.0001

Data Index: 449140 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7881. Min Act: -0.0001

Data Index: 397399 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7607. Min Act: -0.0001

Data Index: 105077 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7294. Min Act: -0.0001

Data Index: 1244038 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7243. Min Act: -0.0001

Data Index: 761725 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7465. Min Act: -0.0001

Data Index: 228250 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7436. Min Act: -0.0001

Data Index: 263347 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1350094 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1257852 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.6970. Min Act: -0.0001

Data Index: 41214 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.1900. Min Range: -1.1900

Max Act: 0.7185. Min Act: -0.0000

Data Index: 778063 (C4 (Web Text))

Max Activating Token Index: 1020