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

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

Neuron 3059 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1212266 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0292. Min Act: -0.0000

Data Index: 1228924 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0281. Min Act: -0.0000

Data Index: 14633 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0256. Min Act: -0.0000

Data Index: 772433 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1148695 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0268. Min Act: -0.0000

Data Index: 492643 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0247. Min Act: -0.0000

Data Index: 740537 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0247. Min Act: -0.0001

Data Index: 144111 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0232. Min Act: -0.0001

Data Index: 618386 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0245. Min Act: -0.0001

Data Index: 428345 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0253. Min Act: -0.0000

Data Index: 116712 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0242. Min Act: -0.0000

Data Index: 625323 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0242. Min Act: -0.0001

Data Index: 707724 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0249. Min Act: -0.0000

Data Index: 345851 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0247. Min Act: -0.0000

Data Index: 918391 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0245. Min Act: -0.0000

Data Index: 848999 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0256. Min Act: -0.0001

Data Index: 620588 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1034132 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1637361 (Python Code)

Max Activating Token Index: 556

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0238. Min Act: -0.0000

Data Index: 939893 (C4 (Web Text))

Max Activating Token Index: 966