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

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

Neuron 1602 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1211412 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1300882 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1249890 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7788. Min Act: -0.0000

Data Index: 241587 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7854. Min Act: -0.0000

Data Index: 841814 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1166107 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7751. Min Act: -0.0000

Data Index: 731804 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7360. Min Act: -0.0000

Data Index: 367714 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6355. Min Act: -0.0000

Data Index: 846529 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.7064. Min Act: -0.0000

Data Index: 610668 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1306894 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6852. Min Act: -0.0000

Data Index: 414334 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6333. Min Act: -0.0000

Data Index: 541349 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6531. Min Act: -0.0000

Data Index: 943205 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6730. Min Act: -0.0000

Data Index: 605942 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6544. Min Act: -0.0000

Data Index: 679714 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6516. Min Act: -0.0000

Data Index: 75657 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6313. Min Act: -0.0000

Data Index: 192353 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1312882 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.8259. Min Range: -0.8259

Max Act: 0.6621. Min Act: -0.0000

Data Index: 252794 (C4 (Web Text))

Max Activating Token Index: 419