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

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

Neuron 1652 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5548. Min Range: -4.5548

Max Act: 4.1877. Min Act: -0.0000

Data Index: 818114 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 4.5548. Min Range: -4.5548

Max Act: 4.5548. Min Act: -0.0000

Data Index: 1137161 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 4.5548. Min Range: -4.5548

Max Act: 4.3517. Min Act: -0.0000

Data Index: 1296384 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 4.5548. Min Range: -4.5548

Max Act: 4.3306. Min Act: -0.0000

Data Index: 1037131 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.7911. Min Act: -0.0000

Data Index: 341997 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.9177. Min Act: -0.0000

Data Index: 1257509 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 4.5548. Min Range: -4.5548

Max Act: 4.0616. Min Act: -0.0000

Data Index: 214591 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.8049. Min Act: -0.0000

Data Index: 256731 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.5332. Min Act: -0.0000

Data Index: 760140 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.7075. Min Act: -0.0000

Data Index: 376156 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.5556. Min Act: -0.0000

Data Index: 250884 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.5490. Min Act: -0.0000

Data Index: 1352553 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.5126. Min Act: -0.0000

Data Index: 366467 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.5265. Min Act: -0.0000

Data Index: 973050 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.5054. Min Act: -0.0000

Data Index: 490985 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.6461. Min Act: -0.0000

Data Index: 43309 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.4320. Min Act: -0.0000

Data Index: 1077839 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.4151. Min Act: -0.0000

Data Index: 1238866 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.3867. Min Act: -0.0000

Data Index: 1243638 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 4.5548. Min Range: -4.5548

Max Act: 3.3544. Min Act: -0.0000

Data Index: 357267 (C4 (Web Text))

Max Activating Token Index: 5