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

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

Neuron 3572 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2085. Min Act: -0.0002

Data Index: 1342201 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2657. Min Act: -0.0001

Data Index: 567199 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1343405 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2508. Min Act: -0.0002

Data Index: 1088023 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2491. Min Act: -0.0002

Data Index: 468609 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2366. Min Act: -0.0001

Data Index: 54800 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2349. Min Act: -0.0001

Data Index: 1053892 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2440. Min Act: -0.0001

Data Index: 885082 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2336. Min Act: -0.0002

Data Index: 679561 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2207. Min Act: -0.0001

Data Index: 629252 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2255. Min Act: -0.0002

Data Index: 1225108 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2491. Min Act: -0.0002

Data Index: 297098 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2425. Min Act: -0.0001

Data Index: 3315 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1200742 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2103. Min Act: -0.0002

Data Index: 863399 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2123. Min Act: -0.0002

Data Index: 598401 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2171. Min Act: -0.0001

Data Index: 4375 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2071. Min Act: -0.0001

Data Index: 893827 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2059. Min Act: -0.0001

Data Index: 899404 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2221. Min Act: -0.0001

Data Index: 134334 (C4 (Web Text))

Max Activating Token Index: 933