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

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

Neuron 2780 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: 1.3549. Min Range: -1.3549

Max Act: 1.3549. Min Act: -0.0000

Data Index: 421134 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1561723 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1594341 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.8909. Min Act: -0.0000

Data Index: 310588 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.7369. Min Act: -0.0000

Data Index: 302371 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.8082. Min Act: -0.0000

Data Index: 315425 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.8067. Min Act: -0.0000

Data Index: 315959 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1468031 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1635576 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1196557 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.7690. Min Act: -0.0000

Data Index: 632096 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.7633. Min Act: -0.0000

Data Index: 630579 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1629452 (Python Code)

Max Activating Token Index: 604

Text #13

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.7377. Min Act: -0.0000

Data Index: 163773 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.6907. Min Act: -0.0000

Data Index: 284171 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1463285 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.6472. Min Act: -0.0000

Data Index: 100970 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.6233. Min Act: -0.0000

Data Index: 160850 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.6579. Min Act: -0.0000

Data Index: 629093 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.3549. Min Range: -1.3549

Max Act: 0.6286. Min Act: -0.0000

Data Index: 74911 (C4 (Web Text))

Max Activating Token Index: 117