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

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

Neuron 801 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1164. Min Act: -0.0002

Data Index: 693609 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0882. Min Act: -0.0002

Data Index: 494170 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1038. Min Act: -0.0002

Data Index: 245300 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1278442 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0958. Min Act: -0.0002

Data Index: 421450 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0856. Min Act: -0.0002

Data Index: 497728 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1279622 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1254834 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0764. Min Act: -0.0002

Data Index: 687209 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0729. Min Act: -0.0002

Data Index: 407021 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0758. Min Act: -0.0002

Data Index: 557141 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0765. Min Act: -0.0002

Data Index: 701624 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1279545 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0667. Min Act: -0.0002

Data Index: 673298 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1003951 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0672. Min Act: -0.0002

Data Index: 863079 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0618. Min Act: -0.0002

Data Index: 771269 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0609. Min Act: -0.0002

Data Index: 290833 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1436188 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0542. Min Act: -0.0002

Data Index: 206295 (C4 (Web Text))

Max Activating Token Index: 508