Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3311 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1618496 (Python Code)

Max Activating Token Index: 720

Text #1

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1305101 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1595251 (Python Code)

Max Activating Token Index: 533

Text #3

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0278. Min Act: -0.0003

Data Index: 832307 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0252. Min Act: -0.0003

Data Index: 943321 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1633622 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1458792 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1258064 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1538701 (Python Code)

Max Activating Token Index: 345

Text #9

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0278. Min Act: -0.0003

Data Index: 18411 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0260. Min Act: -0.0003

Data Index: 321409 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0262. Min Act: -0.0003

Data Index: 631965 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0262. Min Act: -0.0003

Data Index: 699735 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0265. Min Act: -0.0003

Data Index: 469134 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0265. Min Act: -0.0003

Data Index: 420894 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1577498 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0249. Min Act: -0.0004

Data Index: 1081753 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0263. Min Act: -0.0003

Data Index: 359191 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1616832 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1336798 (C4 (Web Text))

Max Activating Token Index: 366