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

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

Neuron 5409 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.4909. Min Act: -0.0000

Data Index: 592829 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1465677 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1268888 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1591512 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1563244 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2727. Min Act: -0.0000

Data Index: 10237 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1399247 (Python Code)

Max Activating Token Index: 260

Text #7

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2747. Min Act: -0.0000

Data Index: 483585 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1490785 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2613. Min Act: -0.0000

Data Index: 571483 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2685. Min Act: -0.0000

Data Index: 281130 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1526196 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1391236 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1438702 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1447246 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1556970 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2506. Min Act: -0.0000

Data Index: 301035 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1540262 (Python Code)

Max Activating Token Index: 234

Text #18

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1537863 (Python Code)

Max Activating Token Index: 527

Text #19

Max Range: 0.4909. Min Range: -0.4909

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1319470 (C4 (Web Text))

Max Activating Token Index: 848