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

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

Neuron 1340 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: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1345399 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1491768 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0006

Data Index: 518791 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1384248 (Python Code)

Max Activating Token Index: 591

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1389664 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0006

Data Index: 170082 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0040. Min Act: -0.0005

Data Index: 1550859 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0040. Min Act: -0.0005

Data Index: 1559187 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0040. Min Act: -0.0006

Data Index: 437293 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0006

Data Index: 323089 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0005

Data Index: 1521830 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0006

Data Index: 75402 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0038. Min Act: -0.0006

Data Index: 293792 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0005

Data Index: 1418514 (Python Code)

Max Activating Token Index: 346

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0038. Min Act: -0.0006

Data Index: 710958 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0039. Min Act: -0.0006

Data Index: 1091216 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0038. Min Act: -0.0005

Data Index: 1366453 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0037. Min Act: -0.0005

Data Index: 1460764 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0037. Min Act: -0.0006

Data Index: 337273 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0037. Min Act: -0.0006

Data Index: 505449 (C4 (Web Text))

Max Activating Token Index: 732