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

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

Neuron 1254 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.8213. Min Act: -0.0000

Data Index: 232288 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1330185 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5067. Min Act: -0.0001

Data Index: 1214794 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4872. Min Act: -0.0000

Data Index: 510416 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5031. Min Act: -0.0000

Data Index: 984030 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5102. Min Act: -0.0000

Data Index: 495192 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5433. Min Act: -0.0000

Data Index: 239902 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1179226 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1143518 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4724. Min Act: -0.0001

Data Index: 928917 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1190054 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1091294 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1184586 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4977. Min Act: -0.0000

Data Index: 830157 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4514. Min Act: -0.0001

Data Index: 989197 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4646. Min Act: -0.0001

Data Index: 636248 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4423. Min Act: -0.0001

Data Index: 975078 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4300. Min Act: -0.0000

Data Index: 272662 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4638. Min Act: -0.0001

Data Index: 1526773 (Python Code)

Max Activating Token Index: 830

Text #19

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4361. Min Act: -0.0001

Data Index: 1010434 (C4 (Web Text))

Max Activating Token Index: 297