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

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

Neuron 3773 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: 0.7978. Min Range: -0.7978

Max Act: 0.7180. Min Act: -0.0000

Data Index: 351865 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7978. Min Act: -0.0000

Data Index: 832910 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7666. Min Act: -0.0000

Data Index: 583189 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7216. Min Act: -0.0000

Data Index: 289025 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7561. Min Act: -0.0000

Data Index: 784453 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7176. Min Act: -0.0000

Data Index: 445617 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6958. Min Act: -0.0000

Data Index: 762244 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7021. Min Act: -0.0000

Data Index: 971522 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5963. Min Act: -0.0000

Data Index: 924001 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6355. Min Act: -0.0000

Data Index: 483359 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6183. Min Act: -0.0000

Data Index: 92151 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6357. Min Act: -0.0000

Data Index: 146142 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6500. Min Act: -0.0000

Data Index: 166811 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5991. Min Act: -0.0000

Data Index: 90107 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6217. Min Act: -0.0000

Data Index: 627415 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1075108 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1309892 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1004348 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5422. Min Act: -0.0000

Data Index: 58786 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5741. Min Act: -0.0000

Data Index: 586488 (C4 (Web Text))

Max Activating Token Index: 499