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

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

Neuron 4894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1198043 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0218. Min Act: -0.0000

Data Index: 1622240 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0184. Min Act: -0.0000

Data Index: 1527138 (Python Code)

Max Activating Token Index: 994

Text #3

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0164. Min Act: -0.0001

Data Index: 82541 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0179. Min Act: -0.0001

Data Index: 326074 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0205. Min Act: -0.0000

Data Index: 1575130 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1557683 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1018563 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0158. Min Act: -0.0000

Data Index: 1360304 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0149. Min Act: -0.0000

Data Index: 1580992 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0176. Min Act: -0.0001

Data Index: 260044 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0153. Min Act: -0.0000

Data Index: 1399408 (Python Code)

Max Activating Token Index: 784

Text #12

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0145. Min Act: -0.0000

Data Index: 285202 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0137. Min Act: -0.0000

Data Index: 706819 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0151. Min Act: -0.0000

Data Index: 641338 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0139. Min Act: -0.0000

Data Index: 1520791 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0129. Min Act: -0.0001

Data Index: 177984 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0143. Min Act: -0.0000

Data Index: 231156 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0143. Min Act: -0.0001

Data Index: 1382079 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1593246 (Python Code)

Max Activating Token Index: 384