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

Dataset: The Pile

Neuron 1136 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.2344. Min Act: -0.0000

Data Index: 501760 (The Pile)

Max Activating Token Index: 569

Text #1

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.1266. Min Act: -0.0000

Data Index: 345731 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1477596 (The Pile)

Max Activating Token Index: 554

Text #3

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1548228 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1169945 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9905. Min Act: -0.0000

Data Index: 632741 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9173. Min Act: -0.0000

Data Index: 784166 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1600107 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1686508 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1274862 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0438. Min Act: -0.0000

Data Index: 603281 (The Pile)

Max Activating Token Index: 694

Text #11

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1899943 (The Pile)

Max Activating Token Index: 895

Text #12

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9190. Min Act: -0.0000

Data Index: 55150 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8724. Min Act: -0.0000

Data Index: 826593 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9623. Min Act: -0.0000

Data Index: 91646 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8970. Min Act: -0.0000

Data Index: 143145 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1332695 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8720. Min Act: -0.0000

Data Index: 336368 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8815. Min Act: -0.0000

Data Index: 307204 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1772678 (The Pile)

Max Activating Token Index: 718