Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 337 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1232. Min Range: -1.1232

Max Act: 1.1232. Min Act: -0.0002

Data Index: 567009 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 1.1232. Min Range: -1.1232

Max Act: 1.1100. Min Act: -0.0002

Data Index: 163184 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9755. Min Act: -0.0002

Data Index: 1395516 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9349. Min Act: -0.0002

Data Index: 1154893 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9422. Min Act: -0.0002

Data Index: 89582 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9119. Min Act: -0.0002

Data Index: 214334 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9175. Min Act: -0.0002

Data Index: 763823 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9224. Min Act: -0.0002

Data Index: 977165 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9065. Min Act: -0.0002

Data Index: 1581434 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9166. Min Act: -0.0003

Data Index: 875950 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9037. Min Act: -0.0002

Data Index: 815448 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8863. Min Act: -0.0002

Data Index: 599366 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8854. Min Act: -0.0002

Data Index: 270518 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8865. Min Act: -0.0002

Data Index: 473801 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8914. Min Act: -0.0002

Data Index: 1300900 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8547. Min Act: -0.0002

Data Index: 425359 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8545. Min Act: -0.0003

Data Index: 793872 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8513. Min Act: -0.0002

Data Index: 1578669 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8830. Min Act: -0.0002

Data Index: 822066 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8676. Min Act: -0.0002

Data Index: 1625815 (Python Code)

Max Activating Token Index: 782