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

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

Neuron 3580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.9488. Min Act: -0.0001

Data Index: 1631172 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.7448. Min Act: -0.0001

Data Index: 1464341 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.7652. Min Act: -0.0000

Data Index: 1416595 (Python Code)

Max Activating Token Index: 411

Text #3

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.5123. Min Act: -0.0001

Data Index: 1544824 (Python Code)

Max Activating Token Index: 404

Text #4

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.5446. Min Act: -0.0001

Data Index: 1501552 (Python Code)

Max Activating Token Index: 484

Text #5

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.5278. Min Act: -0.0001

Data Index: 1582164 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.4237. Min Act: -0.0000

Data Index: 1613663 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1478025 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.4438. Min Act: -0.0000

Data Index: 1439839 (Python Code)

Max Activating Token Index: 794

Text #9

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1637929 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1488173 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3044. Min Act: -0.0001

Data Index: 1516469 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3164. Min Act: -0.0001

Data Index: 1461487 (Python Code)

Max Activating Token Index: 565

Text #13

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3256. Min Act: 0.0000

Data Index: 1445789 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.2866. Min Act: -0.0001

Data Index: 1602357 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.2775. Min Act: -0.0001

Data Index: 1532462 (Python Code)

Max Activating Token Index: 962

Text #16

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1390204 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1360082 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1377694 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.2792. Min Act: -0.0001

Data Index: 1548462 (Python Code)

Max Activating Token Index: 291