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

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

Neuron 2993 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: 1.2403. Min Range: -1.2403

Max Act: 1.2129. Min Act: -0.0000

Data Index: 717723 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.2196. Min Act: -0.0000

Data Index: 956941 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1115868 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.2403. Min Act: -0.0000

Data Index: 342917 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1249032 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1322112 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1658. Min Act: -0.0000

Data Index: 321380 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1624. Min Act: -0.0000

Data Index: 210555 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1419. Min Act: -0.0000

Data Index: 775964 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1454. Min Act: -0.0000

Data Index: 855085 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1096. Min Act: -0.0000

Data Index: 177467 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1545. Min Act: -0.0000

Data Index: 92069 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1368929 (Python Code)

Max Activating Token Index: 797

Text #13

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1433. Min Act: -0.0000

Data Index: 136074 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1400. Min Act: -0.0000

Data Index: 813461 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1389245 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1249896 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.0981. Min Act: -0.0000

Data Index: 571154 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.0766. Min Act: -0.0000

Data Index: 918238 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.2403. Min Range: -1.2403

Max Act: 1.1397. Min Act: -0.0000

Data Index: 137816 (C4 (Web Text))

Max Activating Token Index: 22