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

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

Neuron 2127 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.2893. Min Act: -0.0000

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 1.2893. Min Range: -1.2893

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1034020 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.9318. Min Act: -0.0000

Data Index: 224514 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.8488. Min Act: -0.0000

Data Index: 319299 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.8215. Min Act: -0.0000

Data Index: 203731 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.8774. Min Act: -0.0000

Data Index: 354003 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.8018. Min Act: -0.0000

Data Index: 743562 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.7598. Min Act: -0.0000

Data Index: 759662 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1308775 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1018488 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.8048. Min Act: -0.0000

Data Index: 822430 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.7485. Min Act: -0.0000

Data Index: 37642 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.7474. Min Act: -0.0000

Data Index: 110682 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.7422. Min Act: -0.0000

Data Index: 916197 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1011580 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.7222. Min Act: -0.0000

Data Index: 66410 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.6930. Min Act: -0.0000

Data Index: 588752 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.6956. Min Act: -0.0000

Data Index: 518603 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.2893. Min Range: -1.2893

Max Act: 0.7132. Min Act: -0.0000

Data Index: 451928 (C4 (Web Text))

Max Activating Token Index: 99