Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2800 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3965. Min Act: -0.0001

Data Index: 198450 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4189. Min Act: -0.0001

Data Index: 1332822 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4339. Min Act: -0.0001

Data Index: 1239618 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4319. Min Act: -0.0001

Data Index: 595489 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4196. Min Act: -0.0001

Data Index: 629238 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1015646 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3957. Min Act: -0.0001

Data Index: 283939 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4087. Min Act: -0.0001

Data Index: 865519 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3947. Min Act: -0.0001

Data Index: 517261 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3807. Min Act: -0.0001

Data Index: 562604 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4205. Min Act: -0.0001

Data Index: 109217 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3843. Min Act: -0.0001

Data Index: 1083678 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3785. Min Act: -0.0001

Data Index: 220183 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3816. Min Act: -0.0001

Data Index: 1134926 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4051. Min Act: -0.0001

Data Index: 899727 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3919. Min Act: -0.0001

Data Index: 91019 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3754. Min Act: -0.0001

Data Index: 616947 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3803. Min Act: -0.0001

Data Index: 813623 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3890. Min Act: -0.0001

Data Index: 624397 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3644. Min Act: -0.0001

Data Index: 906500 (C4 (Web Text))

Max Activating Token Index: 503