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

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

Neuron 2000 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: 4.1395. Min Range: -4.1395

Max Act: 3.9950. Min Act: -0.0000

Data Index: 1477770 (Python Code)

Max Activating Token Index: 344

Text #1

Max Range: 4.1395. Min Range: -4.1395

Max Act: 4.1395. Min Act: -0.0000

Data Index: 1601591 (Python Code)

Max Activating Token Index: 514

Text #2

Max Range: 4.1395. Min Range: -4.1395

Max Act: 4.0843. Min Act: -0.0000

Data Index: 1477278 (Python Code)

Max Activating Token Index: 540

Text #3

Max Range: 4.1395. Min Range: -4.1395

Max Act: 4.0581. Min Act: -0.0000

Data Index: 1459147 (Python Code)

Max Activating Token Index: 436

Text #4

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.8924. Min Act: -0.0000

Data Index: 1444893 (Python Code)

Max Activating Token Index: 471

Text #5

Max Range: 4.1395. Min Range: -4.1395

Max Act: 4.0310. Min Act: -0.0000

Data Index: 1531448 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.8686. Min Act: -0.0000

Data Index: 1431273 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.8768. Min Act: -0.0000

Data Index: 1485927 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 4.1395. Min Range: -4.1395

Max Act: 4.0160. Min Act: -0.0000

Data Index: 1636683 (Python Code)

Max Activating Token Index: 547

Text #9

Max Range: 4.1395. Min Range: -4.1395

Max Act: 4.0141. Min Act: -0.0000

Data Index: 1551338 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.8023. Min Act: -0.0000

Data Index: 1417707 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.8112. Min Act: -0.0000

Data Index: 1438000 (Python Code)

Max Activating Token Index: 442

Text #12

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.9501. Min Act: -0.0000

Data Index: 1421862 (Python Code)

Max Activating Token Index: 625

Text #13

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.7797. Min Act: -0.0000

Data Index: 1453923 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.9271. Min Act: -0.0000

Data Index: 1449974 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.7247. Min Act: -0.0000

Data Index: 1532979 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.7286. Min Act: -0.0000

Data Index: 1616269 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.8831. Min Act: -0.0000

Data Index: 1636140 (Python Code)

Max Activating Token Index: 455

Text #18

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.8892. Min Act: -0.0000

Data Index: 1360243 (Python Code)

Max Activating Token Index: 474

Text #19

Max Range: 4.1395. Min Range: -4.1395

Max Act: 3.7380. Min Act: -0.0000

Data Index: 1614998 (Python Code)

Max Activating Token Index: 282