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

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

Neuron 259 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.1072. Min Act: -0.0000

Data Index: 867418 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.2185. Min Act: -0.0000

Data Index: 487171 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1041771 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1224090 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1331481 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.0136. Min Act: -0.0000

Data Index: 344039 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.0632. Min Act: -0.0000

Data Index: 939704 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.8846. Min Act: -0.0000

Data Index: 329984 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.0323. Min Act: -0.0000

Data Index: 174998 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1354464 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.9744. Min Act: -0.0000

Data Index: 1119701 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.9138. Min Act: -0.0000

Data Index: 642534 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.0478. Min Act: -0.0000

Data Index: 220623 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 1.2185. Min Range: -1.2185

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1357928 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.9104. Min Act: -0.0000

Data Index: 392787 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.9152. Min Act: -0.0000

Data Index: 944520 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.9093. Min Act: -0.0000

Data Index: 435517 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.9299. Min Act: -0.0000

Data Index: 543731 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.8718. Min Act: -0.0000

Data Index: 857427 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.2185. Min Range: -1.2185

Max Act: 0.9360. Min Act: -0.0000

Data Index: 859539 (C4 (Web Text))

Max Activating Token Index: 862