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

Dataset: The Pile

Neuron 1524 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.8305. Min Act: -0.0000

Data Index: 209401 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1649322 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1829404 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.7355. Min Act: -0.0000

Data Index: 253910 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1852551 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1053461 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6258. Min Act: 0.0000

Data Index: 1234180 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1091828 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1576592 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1568465 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1422815 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6357. Min Act: 0.0000

Data Index: 1565727 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1818169 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.5800. Min Act: 0.0000

Data Index: 1820009 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.5950. Min Act: 0.0000

Data Index: 208892 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.5931. Min Act: -0.0000

Data Index: 407969 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6281. Min Act: -0.0000

Data Index: 103701 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1893135 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1147523 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.8305. Min Range: -0.8305

Max Act: 0.6015. Min Act: -0.0000

Data Index: 671865 (The Pile)

Max Activating Token Index: 515