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

Dataset: The Pile

Neuron 1300 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: 0.4980. Min Range: -0.4980

Max Act: 0.4980. Min Act: -0.0000

Data Index: 467366 (The Pile)

Max Activating Token Index: 725

Text #1

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1362054 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1158892 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4404. Min Act: -0.0000

Data Index: 491590 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4526. Min Act: -0.0000

Data Index: 839944 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4778. Min Act: -0.0000

Data Index: 518334 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4555. Min Act: -0.0000

Data Index: 362866 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1437269 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4743. Min Act: -0.0000

Data Index: 193920 (The Pile)

Max Activating Token Index: 934

Text #9

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1237609 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1035659 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4061. Min Act: -0.0000

Data Index: 445851 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4387. Min Act: -0.0000

Data Index: 927041 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4423. Min Act: -0.0000

Data Index: 599413 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4349. Min Act: -0.0000

Data Index: 123490 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4045. Min Act: -0.0000

Data Index: 2198 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1802406 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.3809. Min Act: -0.0000

Data Index: 119496 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.3810. Min Act: -0.0000

Data Index: 276855 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 0.4980. Min Range: -0.4980

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1396552 (The Pile)

Max Activating Token Index: 885