Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3841 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.7338. Min Act: -0.0000

Data Index: 156562 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.6054. Min Act: -0.0000

Data Index: 289075 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.4225. Min Act: -0.0000

Data Index: 1558487 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.4604. Min Act: -0.0000

Data Index: 271188 (The Pile)

Max Activating Token Index: 59

Text #4

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.3703. Min Act: -0.0000

Data Index: 1467986 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.3426. Min Act: -0.0000

Data Index: 156367 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1558499 (The Pile)

Max Activating Token Index: 821

Text #7

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2869. Min Act: -0.0000

Data Index: 1829230 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2597. Min Act: -0.0000

Data Index: 1211445 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1600926 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.3245. Min Act: -0.0000

Data Index: 524490 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2375. Min Act: -0.0000

Data Index: 192421 (The Pile)

Max Activating Token Index: 612

Text #12

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.1981. Min Act: -0.0000

Data Index: 802727 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.1785. Min Act: -0.0000

Data Index: 530535 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.1885. Min Act: -0.0000

Data Index: 230417 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1680988 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.0790. Min Act: -0.0000

Data Index: 394281 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.1576. Min Act: -0.0000

Data Index: 720826 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.2199. Min Act: -0.0000

Data Index: 1454416 (The Pile)

Max Activating Token Index: 625

Text #19

Max Range: 1.7338. Min Range: -1.7338

Max Act: 1.1405. Min Act: -0.0000

Data Index: 787088 (The Pile)

Max Activating Token Index: 442