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

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

Neuron 78 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.9212. Min Act: -0.0000

Data Index: 708442 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.9027. Min Act: -0.0000

Data Index: 890492 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.8060. Min Act: -0.0000

Data Index: 588704 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.8191. Min Act: -0.0000

Data Index: 545538 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.8156. Min Act: -0.0000

Data Index: 58299 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7354. Min Act: -0.0000

Data Index: 830491 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7514. Min Act: -0.0000

Data Index: 159517 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7425. Min Act: -0.0000

Data Index: 410246 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7241. Min Act: -0.0000

Data Index: 773368 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7413. Min Act: -0.0000

Data Index: 74199 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7413. Min Act: -0.0000

Data Index: 388905 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1323325 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7374. Min Act: -0.0000

Data Index: 290979 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7156. Min Act: -0.0000

Data Index: 43005 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7065. Min Act: -0.0000

Data Index: 605589 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6788. Min Act: -0.0000

Data Index: 47602 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1313406 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1086148 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.7062. Min Act: -0.0000

Data Index: 736565 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.9212. Min Range: -0.9212

Max Act: 0.6800. Min Act: -0.0000

Data Index: 487482 (C4 (Web Text))

Max Activating Token Index: 337