Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1136 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0746. Min Range: -1.0746

Max Act: 1.0224. Min Act: -0.0002

Data Index: 871278 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.0746. Min Range: -1.0746

Max Act: 1.0746. Min Act: -0.0002

Data Index: 1345679 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.9379. Min Act: -0.0002

Data Index: 476642 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8253. Min Act: -0.0002

Data Index: 1249552 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8437. Min Act: -0.0002

Data Index: 889898 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8105. Min Act: -0.0002

Data Index: 526417 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8701. Min Act: -0.0002

Data Index: 127832 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8677. Min Act: -0.0002

Data Index: 987008 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8565. Min Act: -0.0002

Data Index: 774353 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7737. Min Act: -0.0002

Data Index: 769527 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8325. Min Act: -0.0002

Data Index: 919352 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8714. Min Act: -0.0002

Data Index: 1262219 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8976. Min Act: -0.0003

Data Index: 245707 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7300. Min Act: -0.0002

Data Index: 334537 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8027. Min Act: -0.0002

Data Index: 1137089 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8206. Min Act: -0.0002

Data Index: 140744 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.9297. Min Act: -0.0002

Data Index: 387011 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 1.0746. Min Range: -1.0746

Max Act: 1.0006. Min Act: -0.0002

Data Index: 764964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.7978. Min Act: -0.0002

Data Index: 976600 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.0746. Min Range: -1.0746

Max Act: 0.8379. Min Act: -0.0002

Data Index: 322789 (C4 (Web Text))

Max Activating Token Index: 384