Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1887 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6985. Min Act: -0.0000

Data Index: 286354 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6634. Min Act: -0.0000

Data Index: 534161 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1280251 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1292788 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6281. Min Act: -0.0000

Data Index: 991472 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6475. Min Act: -0.0000

Data Index: 599893 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6256. Min Act: -0.0000

Data Index: 916714 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6183. Min Act: -0.0000

Data Index: 76470 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1340379 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1353269 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1279175 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5201. Min Act: -0.0000

Data Index: 801022 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5306. Min Act: -0.0000

Data Index: 700242 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1019371 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4831. Min Act: -0.0000

Data Index: 316708 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1265354 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4612. Min Act: -0.0000

Data Index: 422091 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4802. Min Act: -0.0000

Data Index: 804599 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4634. Min Act: 0.0000

Data Index: 146966 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4720. Min Act: -0.0000

Data Index: 332977 (C4 (Web Text))

Max Activating Token Index: 336