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

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

Neuron 1572 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6554. Min Range: -2.6554

Max Act: 2.6554. Min Act: -0.0000

Data Index: 1184881 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 2.6554. Min Range: -2.6554

Max Act: 2.0261. Min Act: -0.0000

Data Index: 298130 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 2.6554. Min Range: -2.6554

Max Act: 2.0410. Min Act: -0.0000

Data Index: 954821 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.9264. Min Act: -0.0000

Data Index: 280715 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.6691. Min Act: -0.0000

Data Index: 391925 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.7137. Min Act: -0.0000

Data Index: 157696 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.7025. Min Act: -0.0000

Data Index: 436785 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.6921. Min Act: -0.0000

Data Index: 766648 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.6836. Min Act: -0.0000

Data Index: 344693 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.5113. Min Act: -0.0000

Data Index: 758056 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.6352. Min Act: -0.0000

Data Index: 284007 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.5236. Min Act: -0.0000

Data Index: 686473 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.5264. Min Act: -0.0000

Data Index: 448936 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.5132. Min Act: -0.0000

Data Index: 389236 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.5033. Min Act: 0.0000

Data Index: 491380 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.5216. Min Act: -0.0000

Data Index: 1098507 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.5830. Min Act: -0.0000

Data Index: 796642 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.3848. Min Act: -0.0000

Data Index: 1073980 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1327167 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 2.6554. Min Range: -2.6554

Max Act: 1.5212. Min Act: -0.0000

Data Index: 28362 (C4 (Web Text))

Max Activating Token Index: 68