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

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

Neuron 503 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: 2.8962. Min Range: -2.8962

Max Act: 2.8962. Min Act: -0.0000

Data Index: 985094 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 2.8962. Min Range: -2.8962

Max Act: 2.2880. Min Act: -0.0000

Data Index: 952240 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 2.8962. Min Range: -2.8962

Max Act: 2.2474. Min Act: -0.0000

Data Index: 344087 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 2.8962. Min Range: -2.8962

Max Act: 2.1332. Min Act: -0.0000

Data Index: 1139665 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 2.8962. Min Range: -2.8962

Max Act: 2.0474. Min Act: -0.0000

Data Index: 1016772 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.9844. Min Act: -0.0000

Data Index: 637211 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 2.8962. Min Range: -2.8962

Max Act: 2.0239. Min Act: -0.0000

Data Index: 483267 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.9987. Min Act: -0.0000

Data Index: 1286288 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.8726. Min Act: -0.0000

Data Index: 949391 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.9873. Min Act: -0.0000

Data Index: 357673 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.9381. Min Act: -0.0000

Data Index: 1101725 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.9502. Min Act: -0.0000

Data Index: 512411 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.8212. Min Act: -0.0000

Data Index: 594877 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.7520. Min Act: -0.0000

Data Index: 83378 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.9105. Min Act: -0.0000

Data Index: 431312 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.6885. Min Act: -0.0000

Data Index: 551867 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.7709. Min Act: -0.0000

Data Index: 913074 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.8635. Min Act: -0.0000

Data Index: 434525 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.6688. Min Act: -0.0000

Data Index: 974337 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 2.8962. Min Range: -2.8962

Max Act: 1.7472. Min Act: -0.0000

Data Index: 365376 (C4 (Web Text))

Max Activating Token Index: 572