Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2422 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6994. Min Act: -0.0001

Data Index: 453306 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6623. Min Act: -0.0001

Data Index: 26614 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5910. Min Act: -0.0001

Data Index: 598150 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6492. Min Act: -0.0001

Data Index: 877016 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6253. Min Act: -0.0001

Data Index: 872036 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5949. Min Act: -0.0001

Data Index: 361072 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6038. Min Act: -0.0001

Data Index: 631427 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5850. Min Act: -0.0001

Data Index: 889188 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6001. Min Act: -0.0001

Data Index: 685924 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5770. Min Act: -0.0001

Data Index: 327743 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5753. Min Act: -0.0001

Data Index: 1049445 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5641. Min Act: -0.0001

Data Index: 989805 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5700. Min Act: -0.0001

Data Index: 291197 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5432. Min Act: -0.0001

Data Index: 340085 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6031. Min Act: -0.0001

Data Index: 659510 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1300933 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5749. Min Act: -0.0001

Data Index: 166569 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5959. Min Act: -0.0001

Data Index: 1200392 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5963. Min Act: -0.0001

Data Index: 238942 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5734. Min Act: -0.0001

Data Index: 1042138 (C4 (Web Text))

Max Activating Token Index: 260