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

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

Neuron 4294 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: 0.7996. Min Range: -0.7996

Max Act: 0.7503. Min Act: -0.0002

Data Index: 1462367 (Python Code)

Max Activating Token Index: 552

Text #1

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7586. Min Act: -0.0002

Data Index: 1482956 (Python Code)

Max Activating Token Index: 416

Text #2

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6405. Min Act: -0.0002

Data Index: 1393100 (Python Code)

Max Activating Token Index: 680

Text #3

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7996. Min Act: -0.0002

Data Index: 1557476 (Python Code)

Max Activating Token Index: 665

Text #4

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7354. Min Act: -0.0002

Data Index: 1484141 (Python Code)

Max Activating Token Index: 267

Text #5

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7178. Min Act: -0.0002

Data Index: 1467769 (Python Code)

Max Activating Token Index: 130

Text #6

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7015. Min Act: -0.0002

Data Index: 1568403 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6983. Min Act: -0.0002

Data Index: 1535101 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7151. Min Act: -0.0002

Data Index: 1654468 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7040. Min Act: -0.0002

Data Index: 1588122 (Python Code)

Max Activating Token Index: 190

Text #10

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6864. Min Act: -0.0002

Data Index: 1593191 (Python Code)

Max Activating Token Index: 583

Text #11

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7327. Min Act: -0.0002

Data Index: 1544746 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6341. Min Act: -0.0002

Data Index: 1398044 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7050. Min Act: -0.0002

Data Index: 1550374 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6871. Min Act: -0.0002

Data Index: 1404603 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7037. Min Act: -0.0002

Data Index: 1454630 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7146. Min Act: -0.0002

Data Index: 1456610 (Python Code)

Max Activating Token Index: 901

Text #17

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6771. Min Act: -0.0002

Data Index: 1653666 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.6328. Min Act: -0.0002

Data Index: 1641932 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 0.7996. Min Range: -0.7996

Max Act: 0.7125. Min Act: -0.0002

Data Index: 1590291 (Python Code)

Max Activating Token Index: 704