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

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

Neuron 3499 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6996. Min Act: -0.0000

Data Index: 390812 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.7038. Min Act: -0.0000

Data Index: 494223 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6509. Min Act: -0.0000

Data Index: 659014 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1356880 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5720. Min Act: -0.0000

Data Index: 854734 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5660. Min Act: -0.0000

Data Index: 607748 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5253. Min Act: -0.0000

Data Index: 975984 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5722. Min Act: -0.0000

Data Index: 26757 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5559. Min Act: -0.0000

Data Index: 534453 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5428. Min Act: -0.0000

Data Index: 272230 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5103. Min Act: -0.0000

Data Index: 639789 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5535. Min Act: -0.0000

Data Index: 158554 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1186224 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1066940 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4438. Min Act: -0.0000

Data Index: 274015 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4835. Min Act: -0.0000

Data Index: 347450 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4168. Min Act: -0.0000

Data Index: 855709 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1204743 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4424. Min Act: -0.0000

Data Index: 649382 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4510. Min Act: -0.0000

Data Index: 301389 (C4 (Web Text))

Max Activating Token Index: 186