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

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

Neuron 1481 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0368. Min Range: -1.0368

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1228641 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.9835. Min Act: -0.0000

Data Index: 913097 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.9894. Min Act: -0.0000

Data Index: 874415 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.9264. Min Act: -0.0000

Data Index: 826735 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.9185. Min Act: -0.0000

Data Index: 684121 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.9480. Min Act: -0.0000

Data Index: 639671 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.9197. Min Act: -0.0001

Data Index: 1418567 (Python Code)

Max Activating Token Index: 905

Text #7

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.8879. Min Act: -0.0000

Data Index: 90922 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1205265 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.8914. Min Act: -0.0000

Data Index: 499613 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.8458. Min Act: -0.0000

Data Index: 910122 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.7769. Min Act: -0.0001

Data Index: 315016 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.8178. Min Act: -0.0001

Data Index: 21972 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.8738. Min Act: -0.0001

Data Index: 252645 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.7422. Min Act: -0.0001

Data Index: 29400 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.8263. Min Act: -0.0000

Data Index: 727064 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.7761. Min Act: -0.0001

Data Index: 1469022 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.8552. Min Act: -0.0000

Data Index: 773099 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.7230. Min Act: -0.0001

Data Index: 721537 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 1.0368. Min Range: -1.0368

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1586379 (Python Code)

Max Activating Token Index: 98