Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 629 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0182. Min Act: -0.0005

Data Index: 1400800 (Python Code)

Max Activating Token Index: 571

Text #1

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0175. Min Act: -0.0005

Data Index: 1391296 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0165. Min Act: -0.0005

Data Index: 1367222 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1369807 (Python Code)

Max Activating Token Index: 522

Text #4

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0139. Min Act: -0.0005

Data Index: 1325729 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1630827 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1656261 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0135. Min Act: -0.0005

Data Index: 284624 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1482702 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0132. Min Act: -0.0005

Data Index: 1539526 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0131. Min Act: -0.0005

Data Index: 1593964 (Python Code)

Max Activating Token Index: 994

Text #11

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1468300 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1375425 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1426509 (Python Code)

Max Activating Token Index: 938

Text #14

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1377914 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1566089 (Python Code)

Max Activating Token Index: 359

Text #16

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1442255 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0124. Min Act: -0.0005

Data Index: 1471131 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1398298 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1656623 (Python Code)

Max Activating Token Index: 499