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

Dataset: The Pile

Neuron 4646 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.9612. Min Act: -0.0000

Data Index: 1910748 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.6060. Min Act: -0.0000

Data Index: 1992435 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.2779. Min Act: -0.0000

Data Index: 276678 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.3382. Min Act: -0.0000

Data Index: 740504 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.0657. Min Act: -0.0000

Data Index: 1049765 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.3396. Min Act: -0.0000

Data Index: 471157 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.2039. Min Act: -0.0000

Data Index: 1115573 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.3331. Min Act: -0.0000

Data Index: 1705568 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 14.9612. Min Range: -14.9612

Max Act: 13.9855. Min Act: -0.0000

Data Index: 243097 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.1183. Min Act: -0.0000

Data Index: 1251544 (The Pile)

Max Activating Token Index: 442

Text #10

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.1328. Min Act: -0.0000

Data Index: 990890 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.3413. Min Act: -0.0000

Data Index: 814717 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.1365. Min Act: -0.0000

Data Index: 605834 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 14.9612. Min Range: -14.9612

Max Act: 14.0572. Min Act: -0.0000

Data Index: 1838604 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 14.9612. Min Range: -14.9612

Max Act: 13.8356. Min Act: -0.0000

Data Index: 1527969 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 14.9612. Min Range: -14.9612

Max Act: 13.4700. Min Act: -0.0000

Data Index: 1640847 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 14.9612. Min Range: -14.9612

Max Act: 13.9271. Min Act: -0.0000

Data Index: 87834 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 14.9612. Min Range: -14.9612

Max Act: 13.8350. Min Act: -0.0000

Data Index: 817324 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 14.9612. Min Range: -14.9612

Max Act: 13.7577. Min Act: -0.0000

Data Index: 1212432 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 14.9612. Min Range: -14.9612

Max Act: 13.6958. Min Act: -0.0000

Data Index: 1923649 (The Pile)

Max Activating Token Index: 776