Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 469 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.9645. Min Act: -0.0000

Data Index: 845958 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1622237 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.7520. Min Act: -0.0000

Data Index: 99553 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6466. Min Act: -0.0000

Data Index: 804505 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.7232. Min Act: -0.0000

Data Index: 172477 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.7175. Min Act: -0.0000

Data Index: 855171 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.7014. Min Act: 0.0001

Data Index: 867650 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6654. Min Act: -0.0000

Data Index: 752385 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6518. Min Act: 0.0000

Data Index: 547330 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6179. Min Act: 0.0000

Data Index: 1246117 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1086533 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6609. Min Act: 0.0000

Data Index: 382125 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6146. Min Act: 0.0000

Data Index: 609295 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6224. Min Act: -0.0000

Data Index: 188221 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.6275. Min Act: 0.0000

Data Index: 241076 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.5173. Min Act: -0.0000

Data Index: 718721 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.5423. Min Act: -0.0000

Data Index: 22099 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.5518. Min Act: -0.0000

Data Index: 613369 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.5662. Min Act: -0.0000

Data Index: 775370 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.9645. Min Range: -0.9645

Max Act: 0.5721. Min Act: 0.0000

Data Index: 1277065 (C4 (Web Text))

Max Activating Token Index: 663