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

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

Neuron 2559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.3977. Min Act: -0.0001

Data Index: 217578 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.3511. Min Act: -0.0002

Data Index: 460595 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2965. Min Act: -0.0001

Data Index: 1031318 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2460. Min Act: -0.0001

Data Index: 634983 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2544. Min Act: -0.0001

Data Index: 634693 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2525. Min Act: -0.0002

Data Index: 877471 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1049016 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2487. Min Act: -0.0001

Data Index: 973672 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2437. Min Act: -0.0001

Data Index: 81787 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2472. Min Act: -0.0001

Data Index: 582147 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2555. Min Act: -0.0001

Data Index: 68242 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1032961 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2357. Min Act: -0.0002

Data Index: 155863 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2576. Min Act: -0.0001

Data Index: 357446 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2265. Min Act: -0.0002

Data Index: 280882 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2258. Min Act: -0.0001

Data Index: 168596 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2425. Min Act: -0.0001

Data Index: 858410 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2301. Min Act: -0.0001

Data Index: 419830 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2364. Min Act: -0.0001

Data Index: 542968 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.3977. Min Range: -0.3977

Max Act: 0.2274. Min Act: -0.0002

Data Index: 22311 (C4 (Web Text))

Max Activating Token Index: 4