Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2871 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2666. Min Act: -0.0000

Data Index: 219883 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2574. Min Act: -0.0000

Data Index: 730945 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1181517 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2566. Min Act: -0.0000

Data Index: 503992 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2391. Min Act: -0.0000

Data Index: 903965 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2686. Min Act: -0.0000

Data Index: 691118 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1087734 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2257. Min Act: -0.0000

Data Index: 813858 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1334602 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1170517 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2099. Min Act: -0.0000

Data Index: 948204 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1256409 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2154. Min Act: -0.0000

Data Index: 230560 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1989. Min Act: -0.0000

Data Index: 910254 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2025. Min Act: -0.0000

Data Index: 663641 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2080. Min Act: -0.0000

Data Index: 472364 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2073. Min Act: -0.0000

Data Index: 45063 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2061. Min Act: -0.0000

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1963. Min Act: -0.0000

Data Index: 594593 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2083. Min Act: -0.0000

Data Index: 41423 (C4 (Web Text))

Max Activating Token Index: 101