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

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

Neuron 3263 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1673. Min Act: -0.0002

Data Index: 462237 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1465. Min Act: -0.0002

Data Index: 1643747 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1388. Min Act: -0.0002

Data Index: 458263 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1391. Min Act: -0.0002

Data Index: 1469638 (Python Code)

Max Activating Token Index: 473

Text #4

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1243304 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1266. Min Act: -0.0002

Data Index: 1619280 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1515833 (Python Code)

Max Activating Token Index: 383

Text #7

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1615830 (Python Code)

Max Activating Token Index: 219

Text #8

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1238. Min Act: -0.0002

Data Index: 921443 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1206. Min Act: -0.0002

Data Index: 159801 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1189. Min Act: -0.0002

Data Index: 1502500 (Python Code)

Max Activating Token Index: 727

Text #11

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1097210 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1560023 (Python Code)

Max Activating Token Index: 464

Text #13

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1130. Min Act: -0.0002

Data Index: 983660 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1136. Min Act: -0.0002

Data Index: 171487 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1648171 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1129. Min Act: -0.0002

Data Index: 305955 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1228325 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1606071 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 0.1673. Min Range: -0.1673

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1489828 (Python Code)

Max Activating Token Index: 41