Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2128 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0002

Data Index: 635547 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0419. Min Act: -0.0001

Data Index: 627803 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0412. Min Act: -0.0001

Data Index: 71260 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0407. Min Act: -0.0001

Data Index: 394613 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0372. Min Act: -0.0001

Data Index: 345890 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0359. Min Act: -0.0001

Data Index: 988051 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0355. Min Act: -0.0002

Data Index: 627384 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0385. Min Act: -0.0001

Data Index: 26087 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1226062 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0354. Min Act: -0.0001

Data Index: 502999 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1028372 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1145754 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0362. Min Act: -0.0001

Data Index: 176755 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0380. Min Act: -0.0001

Data Index: 773327 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0369. Min Act: -0.0001

Data Index: 855345 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1056801 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0340. Min Act: -0.0001

Data Index: 193104 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1139906 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0349. Min Act: -0.0001

Data Index: 785796 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0358. Min Act: -0.0001

Data Index: 545793 (C4 (Web Text))

Max Activating Token Index: 146