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

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

Neuron 2261 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9060. Min Act: -0.0001

Data Index: 588021 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9832. Min Act: -0.0000

Data Index: 397418 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9099. Min Act: -0.0001

Data Index: 846602 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1258996 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9210. Min Act: -0.0001

Data Index: 498629 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9067. Min Act: -0.0001

Data Index: 1126850 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1336602 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7863. Min Act: -0.0001

Data Index: 1194526 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1605516 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8643. Min Act: -0.0001

Data Index: 1155900 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1347211 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7212. Min Act: -0.0001

Data Index: 1000608 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8121. Min Act: -0.0001

Data Index: 757820 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8728. Min Act: -0.0000

Data Index: 817493 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8167. Min Act: -0.0001

Data Index: 212182 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7179. Min Act: -0.0001

Data Index: 449448 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6777. Min Act: -0.0000

Data Index: 897202 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1416290 (Python Code)

Max Activating Token Index: 997

Text #18

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7774. Min Act: -0.0001

Data Index: 496886 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7083. Min Act: -0.0001

Data Index: 157785 (C4 (Web Text))

Max Activating Token Index: 880