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

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

Neuron 2971 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6331. Min Range: -4.6331

Max Act: 4.6331. Min Act: -0.0000

Data Index: 757732 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 4.6331. Min Range: -4.6331

Max Act: 4.5977. Min Act: -0.0000

Data Index: 1172805 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 4.6331. Min Range: -4.6331

Max Act: 4.0001. Min Act: -0.0000

Data Index: 151782 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 4.6331. Min Range: -4.6331

Max Act: 3.5980. Min Act: -0.0000

Data Index: 422422 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 4.6331. Min Range: -4.6331

Max Act: 4.1898. Min Act: -0.0000

Data Index: 575550 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 4.6331. Min Range: -4.6331

Max Act: 4.2456. Min Act: -0.0000

Data Index: 1217243 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 4.6331. Min Range: -4.6331

Max Act: 3.4098. Min Act: -0.0000

Data Index: 677932 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 4.6331. Min Range: -4.6331

Max Act: 3.2566. Min Act: -0.0000

Data Index: 802501 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 4.6331. Min Range: -4.6331

Max Act: 3.0245. Min Act: -0.0000

Data Index: 306684 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 4.6331. Min Range: -4.6331

Max Act: 3.4183. Min Act: -0.0000

Data Index: 391714 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 4.6331. Min Range: -4.6331

Max Act: 3.2062. Min Act: -0.0000

Data Index: 665865 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 4.6331. Min Range: -4.6331

Max Act: 3.2986. Min Act: -0.0000

Data Index: 1161030 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 4.6331. Min Range: -4.6331

Max Act: 2.8924. Min Act: -0.0000

Data Index: 481635 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 4.6331. Min Range: -4.6331

Max Act: 2.6591. Min Act: -0.0000

Data Index: 452918 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 4.6331. Min Range: -4.6331

Max Act: 2.6143. Min Act: -0.0000

Data Index: 104908 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 4.6331. Min Range: -4.6331

Max Act: 2.7176. Min Act: -0.0000

Data Index: 647679 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 4.6331. Min Range: -4.6331

Max Act: 2.6616. Min Act: -0.0000

Data Index: 17409 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 4.6331. Min Range: -4.6331

Max Act: 2.6251. Min Act: -0.0000

Data Index: 1042007 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 4.6331. Min Range: -4.6331

Max Act: 2.5078. Min Act: -0.0000

Data Index: 636001 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 4.6331. Min Range: -4.6331

Max Act: 2.7353. Min Act: -0.0000

Data Index: 440468 (C4 (Web Text))

Max Activating Token Index: 931