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

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

Neuron 3819 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1486380 (Python Code)

Max Activating Token Index: 944

Text #1

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0154. Min Act: -0.0002

Data Index: 797205 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0167. Min Act: -0.0002

Data Index: 477865 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1373001 (Python Code)

Max Activating Token Index: 608

Text #4

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1611572 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0158. Min Act: -0.0002

Data Index: 166867 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1347079 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1465966 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1584706 (Python Code)

Max Activating Token Index: 762

Text #9

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1365152 (Python Code)

Max Activating Token Index: 487

Text #10

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1377511 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0142. Min Act: -0.0002

Data Index: 350930 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1462073 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1169731 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1500290 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1652745 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1160008 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1431676 (Python Code)

Max Activating Token Index: 561

Text #18

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1653514 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1544133 (Python Code)

Max Activating Token Index: 257