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

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

Neuron 641 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.4481. Min Act: -0.0001

Data Index: 206409 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 3.4481. Min Range: -3.4481

Max Act: 3.4344. Min Act: -0.0001

Data Index: 365062 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.6799. Min Act: -0.0001

Data Index: 183960 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.7025. Min Act: -0.0001

Data Index: 1005747 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.2422. Min Act: -0.0001

Data Index: 492261 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.7330. Min Act: -0.0000

Data Index: 754770 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.6932. Min Act: -0.0001

Data Index: 137523 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.7893. Min Act: -0.0000

Data Index: 283008 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.6555. Min Act: -0.0001

Data Index: 1350281 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.8855. Min Act: -0.0001

Data Index: 1295832 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.8795. Min Act: -0.0000

Data Index: 624560 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.5813. Min Act: -0.0000

Data Index: 121121 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.8686. Min Act: -0.0001

Data Index: 72793 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.8077. Min Act: -0.0000

Data Index: 1289757 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.5719. Min Act: -0.0001

Data Index: 954876 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.5334. Min Act: -0.0000

Data Index: 1359021 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.6867. Min Act: -0.0000

Data Index: 47625 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.6592. Min Act: -0.0001

Data Index: 247494 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 3.4481. Min Range: -3.4481

Max Act: 1.9163. Min Act: -0.0001

Data Index: 526855 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 3.4481. Min Range: -3.4481

Max Act: 2.6129. Min Act: -0.0000

Data Index: 466197 (C4 (Web Text))

Max Activating Token Index: 329