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

Dataset: The Pile

Neuron 4383 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2525. Min Range: -1.2525

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1251073 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 1.2525. Min Range: -1.2525

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1652578 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 1.2525. Min Range: -1.2525

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1966415 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 1.2525. Min Range: -1.2525

Max Act: 1.1399. Min Act: -0.0000

Data Index: 95441 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 1.2525. Min Range: -1.2525

Max Act: 1.0725. Min Act: -0.0000

Data Index: 851955 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9999. Min Act: -0.0000

Data Index: 821309 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 1.2525. Min Range: -1.2525

Max Act: 1.0040. Min Act: -0.0000

Data Index: 558845 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9887. Min Act: -0.0000

Data Index: 441982 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9854. Min Act: -0.0001

Data Index: 1577125 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 1.2525. Min Range: -1.2525

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1777084 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9150. Min Act: -0.0000

Data Index: 239259 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9064. Min Act: -0.0000

Data Index: 259851 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1847685 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.8703. Min Act: -0.0001

Data Index: 1382656 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9432. Min Act: -0.0001

Data Index: 1211106 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1930089 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.8416. Min Act: -0.0000

Data Index: 667102 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1000357 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.8732. Min Act: -0.0000

Data Index: 474801 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 1.2525. Min Range: -1.2525

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1175225 (The Pile)

Max Activating Token Index: 459