Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1892 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.9359. Min Act: -0.0000

Data Index: 639568 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7368. Min Act: -0.0000

Data Index: 390363 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.6321. Min Act: -0.0000

Data Index: 1237048 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7535. Min Act: -0.0000

Data Index: 441329 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.6143. Min Act: -0.0000

Data Index: 1256488 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.5985. Min Act: -0.0000

Data Index: 201844 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.6174. Min Act: -0.0000

Data Index: 1119691 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.7933. Min Act: -0.0000

Data Index: 213294 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.6155. Min Act: -0.0000

Data Index: 470064 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.5222. Min Act: -0.0000

Data Index: 507792 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.5083. Min Act: -0.0000

Data Index: 535908 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.4225. Min Act: -0.0000

Data Index: 757011 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.1678. Min Act: -0.0000

Data Index: 380728 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.1725. Min Act: -0.0000

Data Index: 781447 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.3073. Min Act: -0.0000

Data Index: 1187870 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 4.9359. Min Range: -4.9359

Max Act: 4.0333. Min Act: -0.0000

Data Index: 169077 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 4.9359. Min Range: -4.9359

Max Act: 3.8623. Min Act: -0.0000

Data Index: 659918 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 4.9359. Min Range: -4.9359

Max Act: 3.9763. Min Act: -0.0000

Data Index: 168810 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 4.9359. Min Range: -4.9359

Max Act: 3.5871. Min Act: -0.0000

Data Index: 134509 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 4.9359. Min Range: -4.9359

Max Act: 3.5903. Min Act: -0.0000

Data Index: 292605 (C4 (Web Text))

Max Activating Token Index: 99