Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 658 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1285135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0324. Min Act: -0.0004

Data Index: 168964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0004

Data Index: 486030 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0318. Min Act: -0.0004

Data Index: 1004690 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0282. Min Act: -0.0004

Data Index: 632718 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0306. Min Act: -0.0004

Data Index: 321619 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0302. Min Act: -0.0004

Data Index: 1493125 (Python Code)

Max Activating Token Index: 824

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0290. Min Act: -0.0004

Data Index: 1115734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0291. Min Act: -0.0004

Data Index: 363632 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0299. Min Act: -0.0004

Data Index: 1130734 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0285. Min Act: -0.0004

Data Index: 952908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1033715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0295. Min Act: -0.0004

Data Index: 938048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0285. Min Act: -0.0004

Data Index: 295453 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0268. Min Act: -0.0004

Data Index: 1091641 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0268. Min Act: -0.0004

Data Index: 692927 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0265. Min Act: -0.0004

Data Index: 1352872 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0254. Min Act: -0.0004

Data Index: 775253 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0262. Min Act: -0.0004

Data Index: 1232276 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0253. Min Act: -0.0004

Data Index: 332519 (C4 (Web Text))

Max Activating Token Index: 1023