Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1653 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0927. Min Range: -1.0927

Max Act: 1.0736. Min Act: -0.0003

Data Index: 1222061 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.0927. Min Range: -1.0927

Max Act: 1.0927. Min Act: -0.0003

Data Index: 508037 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.9140. Min Act: -0.0003

Data Index: 301516 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.9034. Min Act: -0.0003

Data Index: 513898 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8503. Min Act: -0.0003

Data Index: 968181 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8718. Min Act: -0.0003

Data Index: 1065788 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7729. Min Act: -0.0003

Data Index: 1053839 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8480. Min Act: -0.0003

Data Index: 1106389 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8076. Min Act: -0.0003

Data Index: 222248 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7541. Min Act: -0.0003

Data Index: 700440 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8056. Min Act: -0.0003

Data Index: 197805 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7484. Min Act: -0.0003

Data Index: 691477 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.6957. Min Act: -0.0003

Data Index: 58046 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8170. Min Act: -0.0003

Data Index: 612690 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7633. Min Act: -0.0003

Data Index: 25245 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7322. Min Act: -0.0003

Data Index: 943020 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7544. Min Act: -0.0003

Data Index: 623330 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.6100. Min Act: -0.0003

Data Index: 1199039 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7970. Min Act: -0.0003

Data Index: 722051 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7472. Min Act: -0.0003

Data Index: 389395 (C4 (Web Text))

Max Activating Token Index: 441