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

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

Neuron 3571 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: 0.2509. Min Range: -0.2509

Max Act: 0.2509. Min Act: -0.0000

Data Index: 666597 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2300. Min Act: -0.0001

Data Index: 735187 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2115. Min Act: -0.0000

Data Index: 484821 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1331710 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2331. Min Act: -0.0001

Data Index: 94967 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1173761 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2236. Min Act: -0.0000

Data Index: 525924 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2115. Min Act: -0.0001

Data Index: 135619 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2154. Min Act: -0.0001

Data Index: 617925 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2204. Min Act: -0.0000

Data Index: 314130 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1008187 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1290152 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1216781 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2105. Min Act: -0.0001

Data Index: 685889 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1910. Min Act: -0.0000

Data Index: 841631 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2032. Min Act: -0.0000

Data Index: 209483 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1225768 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2023. Min Act: -0.0001

Data Index: 994454 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1918. Min Act: -0.0001

Data Index: 833935 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1681. Min Act: -0.0000

Data Index: 192989 (C4 (Web Text))

Max Activating Token Index: 483