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

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

Neuron 206 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0191. Min Range: -1.0191

Max Act: 1.0191. Min Act: -0.0003

Data Index: 886185 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8988. Min Act: -0.0003

Data Index: 1143746 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8674. Min Act: -0.0003

Data Index: 153043 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8846. Min Act: -0.0003

Data Index: 508769 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8072. Min Act: -0.0003

Data Index: 889433 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7937. Min Act: -0.0002

Data Index: 67224 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7740. Min Act: -0.0002

Data Index: 852496 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7828. Min Act: -0.0002

Data Index: 1024518 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7554. Min Act: -0.0003

Data Index: 192975 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7195. Min Act: -0.0003

Data Index: 1347746 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7067. Min Act: -0.0002

Data Index: 802781 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7011. Min Act: -0.0003

Data Index: 317866 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.6888. Min Act: -0.0003

Data Index: 676750 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.6854. Min Act: -0.0003

Data Index: 520583 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.6771. Min Act: -0.0003

Data Index: 1137862 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.6692. Min Act: -0.0003

Data Index: 113073 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.6823. Min Act: -0.0003

Data Index: 1055844 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.6643. Min Act: -0.0003

Data Index: 1347942 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.6422. Min Act: -0.0003

Data Index: 368175 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.6378. Min Act: -0.0003

Data Index: 949962 (C4 (Web Text))

Max Activating Token Index: 738