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

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

Neuron 5340 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: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1132232 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1011000 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0558. Min Act: -0.0000

Data Index: 590981 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1045789 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1115236 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0458. Min Act: -0.0000

Data Index: 660212 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0451. Min Act: -0.0000

Data Index: 508359 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0437. Min Act: -0.0000

Data Index: 266878 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0434. Min Act: -0.0000

Data Index: 835151 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0420. Min Act: -0.0000

Data Index: 226246 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0400. Min Act: -0.0000

Data Index: 30073 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1014411 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0399. Min Act: -0.0000

Data Index: 410905 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0446. Min Act: -0.0000

Data Index: 1484008 (Python Code)

Max Activating Token Index: 862

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0416. Min Act: -0.0000

Data Index: 1033524 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1310545 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0426. Min Act: -0.0000

Data Index: 1139273 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0429. Min Act: -0.0000

Data Index: 1111410 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0439. Min Act: -0.0000

Data Index: 717071 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0452. Min Act: -0.0000

Data Index: 1133632 (C4 (Web Text))

Max Activating Token Index: 775