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

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

Neuron 2964 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1201487 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0275. Min Act: -0.0001

Data Index: 792745 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0272. Min Act: -0.0001

Data Index: 811584 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0239. Min Act: -0.0001

Data Index: 333208 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0261. Min Act: -0.0001

Data Index: 403479 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1601397 (Python Code)

Max Activating Token Index: 470

Text #6

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0252. Min Act: -0.0001

Data Index: 256219 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0246. Min Act: -0.0001

Data Index: 291728 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1374613 (Python Code)

Max Activating Token Index: 654

Text #9

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0254. Min Act: -0.0001

Data Index: 58423 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1145514 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0250. Min Act: -0.0001

Data Index: 807795 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0243. Min Act: -0.0001

Data Index: 922951 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1261998 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1645345 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1372612 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0238. Min Act: -0.0001

Data Index: 918017 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1347070 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0233. Min Act: -0.0001

Data Index: 356413 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1254722 (C4 (Web Text))

Max Activating Token Index: 589