Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 68 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0215. Min Act: -0.0006

Data Index: 942903 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1549914 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0170. Min Act: -0.0005

Data Index: 1378544 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1626304 (Python Code)

Max Activating Token Index: 206

Text #4

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0165. Min Act: -0.0005

Data Index: 1541154 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0162. Min Act: -0.0006

Data Index: 632481 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0156. Min Act: -0.0005

Data Index: 1374657 (Python Code)

Max Activating Token Index: 445

Text #7

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0159. Min Act: -0.0005

Data Index: 1380815 (Python Code)

Max Activating Token Index: 455

Text #8

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0158. Min Act: -0.0005

Data Index: 1397252 (Python Code)

Max Activating Token Index: 119

Text #9

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0156. Min Act: -0.0005

Data Index: 1561664 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1620575 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0156. Min Act: -0.0006

Data Index: 780007 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0154. Min Act: -0.0005

Data Index: 1521462 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0153. Min Act: -0.0006

Data Index: 216029 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1441646 (Python Code)

Max Activating Token Index: 232

Text #15

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1545060 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0152. Min Act: -0.0004

Data Index: 1597597 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0151. Min Act: -0.0005

Data Index: 1386354 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1122641 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0151. Min Act: -0.0004

Data Index: 1454771 (Python Code)

Max Activating Token Index: 538