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

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

Neuron 4331 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: 0.5482. Min Range: -0.5482

Max Act: 0.5482. Min Act: -0.0000

Data Index: 143821 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.5035. Min Act: -0.0000

Data Index: 178479 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4655. Min Act: -0.0000

Data Index: 494843 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4580. Min Act: -0.0000

Data Index: 66553 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4563. Min Act: -0.0000

Data Index: 685105 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4834. Min Act: -0.0000

Data Index: 322120 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4029. Min Act: -0.0000

Data Index: 653861 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4131. Min Act: -0.0000

Data Index: 849450 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4216. Min Act: -0.0000

Data Index: 204887 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3908. Min Act: -0.0000

Data Index: 420158 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1101800 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1012197 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3660. Min Act: -0.0000

Data Index: 541424 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1151776 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1188790 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3995. Min Act: -0.0000

Data Index: 6556 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1239962 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1276267 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1330274 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.5482. Min Range: -0.5482

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1140699 (C4 (Web Text))

Max Activating Token Index: 990