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

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

Neuron 711 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4588. Min Range: -2.4588

Max Act: 2.4477. Min Act: -0.0000

Data Index: 198610 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 2.4588. Min Range: -2.4588

Max Act: 2.4588. Min Act: -0.0000

Data Index: 760573 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 2.4588. Min Range: -2.4588

Max Act: 2.0336. Min Act: -0.0000

Data Index: 48306 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 2.4588. Min Range: -2.4588

Max Act: 2.2225. Min Act: -0.0000

Data Index: 1260121 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 2.4588. Min Range: -2.4588

Max Act: 2.3120. Min Act: -0.0000

Data Index: 482152 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.9935. Min Act: -0.0000

Data Index: 193169 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.9488. Min Act: -0.0000

Data Index: 984968 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.9982. Min Act: -0.0000

Data Index: 210255 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 2.4588. Min Range: -2.4588

Max Act: 2.0355. Min Act: -0.0000

Data Index: 1295835 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1308732 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 2.4588. Min Range: -2.4588

Max Act: 2.0709. Min Act: -0.0000

Data Index: 29402 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 2.4588. Min Range: -2.4588

Max Act: 2.0461. Min Act: -0.0000

Data Index: 132884 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.6298. Min Act: -0.0000

Data Index: 696969 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.9150. Min Act: -0.0000

Data Index: 1219946 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.7761. Min Act: -0.0000

Data Index: 809619 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.8768. Min Act: -0.0000

Data Index: 971256 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.7613. Min Act: -0.0000

Data Index: 1285840 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.6065. Min Act: -0.0000

Data Index: 627021 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.7853. Min Act: -0.0000

Data Index: 1195651 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 2.4588. Min Range: -2.4588

Max Act: 1.8089. Min Act: -0.0000

Data Index: 912339 (C4 (Web Text))

Max Activating Token Index: 542