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

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

Neuron 558 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1384283 (Python Code)

Max Activating Token Index: 825

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1579411 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1459633 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1649602 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1542142 (Python Code)

Max Activating Token Index: 993

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1428570 (Python Code)

Max Activating Token Index: 840

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1395958 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1540300 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1541248 (Python Code)

Max Activating Token Index: 827

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1473922 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1648610 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0122. Min Act: -0.0003

Data Index: 406571 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0113. Min Act: -0.0002

Data Index: 375382 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1444336 (Python Code)

Max Activating Token Index: 699

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0111. Min Act: -0.0003

Data Index: 995368 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0106. Min Act: -0.0003

Data Index: 347307 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1045415 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0106. Min Act: -0.0002

Data Index: 340113 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0106. Min Act: -0.0002

Data Index: 33328 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0105. Min Act: -0.0003

Data Index: 279167 (C4 (Web Text))

Max Activating Token Index: 782