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

Dataset: The Pile

Neuron 3865 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: 1.2388. Min Range: -1.2388

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1508773 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.1403. Min Act: -0.0000

Data Index: 859606 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.1374. Min Act: -0.0000

Data Index: 359003 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1403748 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0206. Min Act: -0.0000

Data Index: 707341 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1700124 (The Pile)

Max Activating Token Index: 288

Text #6

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0378. Min Act: -0.0000

Data Index: 429630 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1082972 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.2388. Min Range: -1.2388

Max Act: 1.0037. Min Act: -0.0000

Data Index: 390164 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9087. Min Act: -0.0000

Data Index: 953979 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1075127 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9240. Min Act: -0.0000

Data Index: 677910 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1323952 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1749698 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1108313 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8577. Min Act: -0.0000

Data Index: 643588 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.7977. Min Act: -0.0000

Data Index: 952810 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1647022 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8924. Min Act: -0.0000

Data Index: 356207 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 1.2388. Min Range: -1.2388

Max Act: 0.8377. Min Act: -0.0000

Data Index: 143001 (The Pile)

Max Activating Token Index: 757