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

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

Neuron 3430 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7982. Min Act: -0.0000

Data Index: 681055 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7381. Min Act: -0.0000

Data Index: 644783 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1352566 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7915. Min Act: -0.0000

Data Index: 493253 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7260. Min Act: -0.0000

Data Index: 415256 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1318204 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6513. Min Act: -0.0000

Data Index: 336970 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6420. Min Act: -0.0000

Data Index: 161093 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1246670 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6805. Min Act: -0.0000

Data Index: 983774 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6267. Min Act: -0.0000

Data Index: 114078 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6873. Min Act: -0.0000

Data Index: 350759 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6635. Min Act: -0.0000

Data Index: 840952 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1253020 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6334. Min Act: -0.0000

Data Index: 764760 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6226. Min Act: -0.0000

Data Index: 743930 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1147239 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6505. Min Act: -0.0000

Data Index: 418181 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5981. Min Act: -0.0000

Data Index: 632079 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5514. Min Act: -0.0000

Data Index: 376179 (C4 (Web Text))

Max Activating Token Index: 1023