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

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

Neuron 5085 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0000

Data Index: 875769 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0459. Min Act: -0.0000

Data Index: 651878 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0373. Min Act: -0.0000

Data Index: 529953 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0400. Min Act: -0.0000

Data Index: 341803 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1496295 (Python Code)

Max Activating Token Index: 857

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0391. Min Act: -0.0000

Data Index: 131954 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0386. Min Act: -0.0000

Data Index: 221565 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0383. Min Act: -0.0000

Data Index: 127640 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0373. Min Act: -0.0000

Data Index: 338811 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1347365 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1421353 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0303. Min Act: -0.0000

Data Index: 385935 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0369. Min Act: -0.0000

Data Index: 217412 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0354. Min Act: -0.0000

Data Index: 268601 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0267. Min Act: -0.0000

Data Index: 647374 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0313. Min Act: -0.0000

Data Index: 771964 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0329. Min Act: -0.0000

Data Index: 805672 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1205785 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0317. Min Act: -0.0000

Data Index: 201856 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1437040 (Python Code)

Max Activating Token Index: 78