Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2089 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3854. Min Range: -1.3854

Max Act: 1.3854. Min Act: -0.0000

Data Index: 934750 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9615. Min Act: -0.0000

Data Index: 617924 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1264011 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.9051. Min Act: -0.0000

Data Index: 49250 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.8908. Min Act: -0.0000

Data Index: 87402 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1101648 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.8201. Min Act: -0.0000

Data Index: 709700 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.7918. Min Act: -0.0000

Data Index: 946511 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.8246. Min Act: -0.0000

Data Index: 756940 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.7916. Min Act: -0.0000

Data Index: 403688 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.8203. Min Act: -0.0000

Data Index: 321 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.7747. Min Act: -0.0000

Data Index: 691678 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.7406. Min Act: -0.0000

Data Index: 318013 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1192033 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.7065. Min Act: -0.0000

Data Index: 274511 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.6807. Min Act: -0.0000

Data Index: 815075 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.7159. Min Act: -0.0000

Data Index: 778786 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.6675. Min Act: -0.0000

Data Index: 598345 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.6691. Min Act: -0.0000

Data Index: 288637 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 1.3854. Min Range: -1.3854

Max Act: 0.7354. Min Act: -0.0000

Data Index: 801155 (C4 (Web Text))

Max Activating Token Index: 638