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

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

Neuron 541 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: 0.0147. Min Range: -0.0147

Max Act: 0.0147. Min Act: -0.0005

Data Index: 1620721 (Python Code)

Max Activating Token Index: 416

Text #1

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1429988 (Python Code)

Max Activating Token Index: 264

Text #2

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0131. Min Act: -0.0006

Data Index: 500259 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1387802 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0128. Min Act: -0.0006

Data Index: 275998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1391979 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1403223 (Python Code)

Max Activating Token Index: 569

Text #7

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1313462 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1379813 (Python Code)

Max Activating Token Index: 767

Text #9

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1371358 (Python Code)

Max Activating Token Index: 952

Text #10

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0006

Data Index: 237341 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0006

Data Index: 417692 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1320554 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1452533 (Python Code)

Max Activating Token Index: 462

Text #14

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1464850 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1584824 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1447457 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1559562 (Python Code)

Max Activating Token Index: 549

Text #18

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1513827 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1580174 (Python Code)

Max Activating Token Index: 864