Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 585 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0378. Min Act: -0.0002

Data Index: 845105 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1589448 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1509545 (Python Code)

Max Activating Token Index: 357

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0369. Min Act: -0.0001

Data Index: 534547 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0351. Min Act: -0.0002

Data Index: 804576 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0357. Min Act: -0.0002

Data Index: 512275 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1639478 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1094008 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1063762 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1270586 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1626467 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1389791 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1620684 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1171481 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1414812 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0334. Min Act: -0.0002

Data Index: 557646 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1374089 (Python Code)

Max Activating Token Index: 280

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0321. Min Act: -0.0002

Data Index: 207920 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1550670 (Python Code)

Max Activating Token Index: 747

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0320. Min Act: -0.0002

Data Index: 599184 (C4 (Web Text))

Max Activating Token Index: 947