Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3027 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0001

Data Index: 318785 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0332. Min Act: -0.0001

Data Index: 938007 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1040329 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0307. Min Act: -0.0001

Data Index: 771361 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0318. Min Act: -0.0001

Data Index: 187895 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0302. Min Act: -0.0001

Data Index: 133590 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0291. Min Act: -0.0000

Data Index: 556528 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0290. Min Act: -0.0001

Data Index: 120743 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1433142 (Python Code)

Max Activating Token Index: 298

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0292. Min Act: -0.0001

Data Index: 579975 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0291. Min Act: -0.0001

Data Index: 347928 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0299. Min Act: -0.0000

Data Index: 353616 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0266. Min Act: -0.0001

Data Index: 475196 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0292. Min Act: -0.0001

Data Index: 369713 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0296. Min Act: -0.0001

Data Index: 291103 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0295. Min Act: -0.0001

Data Index: 521475 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0289. Min Act: -0.0001

Data Index: 26988 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1514025 (Python Code)

Max Activating Token Index: 486

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1606595 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0281. Min Act: -0.0001

Data Index: 121661 (C4 (Web Text))

Max Activating Token Index: 487