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

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

Neuron 2353 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: 5.9692. Min Range: -5.9692

Max Act: 5.9692. Min Act: -0.0000

Data Index: 668539 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.4138. Min Act: -0.0000

Data Index: 232816 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.4676. Min Act: -0.0000

Data Index: 321585 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.4360. Min Act: -0.0000

Data Index: 464039 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.5096. Min Act: -0.0000

Data Index: 821193 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.2722. Min Act: -0.0000

Data Index: 492003 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.4349. Min Act: -0.0000

Data Index: 675951 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.2026. Min Act: -0.0000

Data Index: 753678 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.3769. Min Act: -0.0000

Data Index: 744024 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.0672. Min Act: -0.0000

Data Index: 866884 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.0153. Min Act: -0.0000

Data Index: 971324 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 5.9692. Min Range: -5.9692

Max Act: 4.7903. Min Act: -0.0000

Data Index: 993082 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 5.9692. Min Range: -5.9692

Max Act: 4.9131. Min Act: -0.0000

Data Index: 646430 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.0754. Min Act: -0.0000

Data Index: 6096 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 5.9692. Min Range: -5.9692

Max Act: 4.7196. Min Act: -0.0000

Data Index: 214835 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 5.9692. Min Range: -5.9692

Max Act: 4.8560. Min Act: -0.0000

Data Index: 904287 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 5.9692. Min Range: -5.9692

Max Act: 5.0527. Min Act: -0.0000

Data Index: 198953 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 5.9692. Min Range: -5.9692

Max Act: 4.2917. Min Act: -0.0000

Data Index: 696353 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 5.9692. Min Range: -5.9692

Max Act: 4.8674. Min Act: -0.0000

Data Index: 980136 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 5.9692. Min Range: -5.9692

Max Act: 4.6350. Min Act: -0.0000

Data Index: 1084975 (C4 (Web Text))

Max Activating Token Index: 750