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

Dataset: The Pile

Neuron 615 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: 1.2176. Min Range: -1.2176

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1852286 (The Pile)

Max Activating Token Index: 507

Text #1

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.2176. Min Act: -0.0000

Data Index: 958300 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.1389. Min Act: -0.0000

Data Index: 417966 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9890. Min Act: -0.0000

Data Index: 412461 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1144303 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1244142 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9429. Min Act: -0.0000

Data Index: 577464 (The Pile)

Max Activating Token Index: 57

Text #7

Max Range: 1.2176. Min Range: -1.2176

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1698295 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1131398 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1786403 (The Pile)

Max Activating Token Index: 2

Text #10

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9870. Min Act: -0.0000

Data Index: 924580 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9726. Min Act: -0.0000

Data Index: 506927 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1424621 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1383291 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1107687 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1263570 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.8985. Min Act: -0.0000

Data Index: 947604 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9974. Min Act: -0.0000

Data Index: 49940 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1229633 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 1.2176. Min Range: -1.2176

Max Act: 0.9455. Min Act: -0.0000

Data Index: 29418 (The Pile)

Max Activating Token Index: 434