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

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

Neuron 5550 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: 1.0343. Min Range: -1.0343

Max Act: 0.9948. Min Act: -0.0000

Data Index: 763044 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.9929. Min Act: -0.0000

Data Index: 71729 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.0343. Min Range: -1.0343

Max Act: 1.0080. Min Act: -0.0000

Data Index: 249100 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.0343. Min Range: -1.0343

Max Act: 1.0343. Min Act: -0.0000

Data Index: 258020 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8376. Min Act: -0.0000

Data Index: 222553 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8621. Min Act: -0.0000

Data Index: 515819 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8439. Min Act: -0.0000

Data Index: 773352 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8319. Min Act: -0.0000

Data Index: 306789 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.8007. Min Act: -0.0000

Data Index: 137943 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7406. Min Act: -0.0000

Data Index: 227147 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7320. Min Act: -0.0000

Data Index: 116307 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7397. Min Act: -0.0000

Data Index: 917727 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1345513 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7209. Min Act: -0.0000

Data Index: 778699 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1113010 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1206291 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1205771 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7015. Min Act: -0.0000

Data Index: 935704 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.6799. Min Act: -0.0000

Data Index: 57495 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.0343. Min Range: -1.0343

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1130343 (C4 (Web Text))

Max Activating Token Index: 250