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

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

Neuron 5974 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8765. Min Act: -0.0000

Data Index: 905338 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 4.8765. Min Range: -4.8765

Max Act: 3.5189. Min Act: -0.0000

Data Index: 1053131 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 4.8765. Min Range: -4.8765

Max Act: 3.6166. Min Act: -0.0000

Data Index: 738790 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 4.8765. Min Range: -4.8765

Max Act: 3.7620. Min Act: -0.0000

Data Index: 325855 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 4.8765. Min Range: -4.8765

Max Act: 3.0739. Min Act: -0.0000

Data Index: 1374680 (Python Code)

Max Activating Token Index: 656

Text #5

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.9096. Min Act: 0.0000

Data Index: 1208520 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 4.8765. Min Range: -4.8765

Max Act: 3.0373. Min Act: 0.0000

Data Index: 363141 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.8418. Min Act: -0.0000

Data Index: 1445602 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 4.8765. Min Range: -4.8765

Max Act: 3.0773. Min Act: -0.0000

Data Index: 502578 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.6420. Min Act: -0.0000

Data Index: 357560 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.7732. Min Act: -0.0000

Data Index: 1396847 (Python Code)

Max Activating Token Index: 937

Text #11

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.6689. Min Act: -0.0000

Data Index: 660123 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.8662. Min Act: -0.0000

Data Index: 1087745 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.5994. Min Act: -0.0000

Data Index: 1049220 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.6010. Min Act: -0.0000

Data Index: 961535 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.6357. Min Act: -0.0000

Data Index: 56289 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.7301. Min Act: -0.0000

Data Index: 392567 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.3836. Min Act: -0.0000

Data Index: 866331 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.5298. Min Act: -0.0000

Data Index: 1388452 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 4.8765. Min Range: -4.8765

Max Act: 2.5065. Min Act: -0.0000

Data Index: 145778 (C4 (Web Text))

Max Activating Token Index: 134