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

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

Neuron 3214 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1267803 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.1068. Min Act: -0.0000

Data Index: 341650 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.9301. Min Act: -0.0000

Data Index: 297114 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8835. Min Act: -0.0000

Data Index: 7940 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.9473. Min Act: -0.0000

Data Index: 212601 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8924. Min Act: -0.0000

Data Index: 18426 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8392. Min Act: -0.0000

Data Index: 472190 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1365590 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1248590 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6837. Min Act: -0.0000

Data Index: 583338 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6953. Min Act: -0.0000

Data Index: 72083 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6196. Min Act: -0.0000

Data Index: 551910 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6678. Min Act: -0.0000

Data Index: 462444 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1194519 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6177. Min Act: -0.0000

Data Index: 938634 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6622. Min Act: -0.0000

Data Index: 819456 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6160. Min Act: -0.0000

Data Index: 510626 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6839. Min Act: -0.0000

Data Index: 154900 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1336977 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1151485 (C4 (Web Text))

Max Activating Token Index: 233