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

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

Neuron 1747 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1181601 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0350. Min Act: -0.0000

Data Index: 19874 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0032. Min Act: -0.0000

Data Index: 209175 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9024. Min Act: -0.0000

Data Index: 873254 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1234797 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1435113 (Python Code)

Max Activating Token Index: 802

Text #6

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1471179 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7721. Min Act: 0.0000

Data Index: 1207972 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.6815. Min Act: -0.0000

Data Index: 469131 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1101907 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7168. Min Act: -0.0000

Data Index: 625863 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7550. Min Act: -0.0000

Data Index: 726767 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7778. Min Act: -0.0000

Data Index: 16448 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.6852. Min Act: -0.0000

Data Index: 8724 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7244. Min Act: -0.0000

Data Index: 844989 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1634982 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.6943. Min Act: -0.0000

Data Index: 371905 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1141326 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.5865. Min Act: -0.0000

Data Index: 308146 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.5841. Min Act: -0.0000

Data Index: 493777 (C4 (Web Text))

Max Activating Token Index: 536