Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1808 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2459. Min Act: -0.0002

Data Index: 336804 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2426. Min Act: -0.0002

Data Index: 439676 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2146. Min Act: -0.0002

Data Index: 1185905 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1999. Min Act: -0.0002

Data Index: 172315 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1938. Min Act: -0.0002

Data Index: 571361 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1944. Min Act: -0.0002

Data Index: 83300 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1906. Min Act: -0.0002

Data Index: 448518 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1948. Min Act: -0.0002

Data Index: 165322 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1875. Min Act: -0.0002

Data Index: 234456 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1829. Min Act: -0.0002

Data Index: 782112 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1818. Min Act: -0.0002

Data Index: 781172 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1803. Min Act: -0.0002

Data Index: 1020704 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1732. Min Act: -0.0002

Data Index: 1215624 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1795. Min Act: -0.0002

Data Index: 578200 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1717. Min Act: -0.0002

Data Index: 695948 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1704. Min Act: -0.0002

Data Index: 536909 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1673. Min Act: -0.0002

Data Index: 363921 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1731. Min Act: -0.0002

Data Index: 116419 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1789. Min Act: -0.0002

Data Index: 153398 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1702. Min Act: -0.0002

Data Index: 824516 (C4 (Web Text))

Max Activating Token Index: 456