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

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

Neuron 2371 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2897. Min Range: -3.2897

Max Act: 3.2897. Min Act: -0.0000

Data Index: 1135702 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 3.2897. Min Range: -3.2897

Max Act: 3.2548. Min Act: -0.0001

Data Index: 347762 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.2897. Min Range: -3.2897

Max Act: 3.0838. Min Act: -0.0000

Data Index: 319602 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.9170. Min Act: -0.0001

Data Index: 255053 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.9342. Min Act: -0.0001

Data Index: 427994 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.9378. Min Act: -0.0000

Data Index: 376171 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.9199. Min Act: -0.0000

Data Index: 704221 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.9913. Min Act: -0.0000

Data Index: 612188 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.6909. Min Act: -0.0000

Data Index: 726195 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.4162. Min Act: -0.0001

Data Index: 948501 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.4914. Min Act: -0.0000

Data Index: 680110 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.4863. Min Act: -0.0001

Data Index: 315715 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.3645. Min Act: -0.0000

Data Index: 873779 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.3556. Min Act: -0.0000

Data Index: 532787 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.7410. Min Act: -0.0000

Data Index: 438565 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.5671. Min Act: -0.0000

Data Index: 1336899 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.5783. Min Act: -0.0000

Data Index: 994031 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.5603. Min Act: -0.0000

Data Index: 1324047 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.4290. Min Act: -0.0000

Data Index: 76381 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 3.2897. Min Range: -3.2897

Max Act: 2.5028. Min Act: -0.0000

Data Index: 814655 (C4 (Web Text))

Max Activating Token Index: 740