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

Dataset: The Pile

Neuron 1797 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1743. Min Act: -0.0000

Data Index: 3834 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1125536 (The Pile)

Max Activating Token Index: 873

Text #2

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1531003 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1071897 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1511. Min Act: -0.0000

Data Index: 800135 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1094. Min Act: -0.0000

Data Index: 321617 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1383723 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1296. Min Act: -0.0000

Data Index: 77485 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1133430 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0736. Min Act: -0.0000

Data Index: 716544 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1552648 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1299660 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1572. Min Act: -0.0000

Data Index: 303428 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0711. Min Act: -0.0000

Data Index: 529706 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1051. Min Act: -0.0000

Data Index: 947705 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.1038. Min Act: -0.0000

Data Index: 308543 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 1.2255. Min Range: -1.2255

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1369069 (The Pile)

Max Activating Token Index: 684

Text #17

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1073077 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0628. Min Act: -0.0000

Data Index: 995679 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 1.2255. Min Range: -1.2255

Max Act: 1.0283. Min Act: -0.0000

Data Index: 956512 (The Pile)

Max Activating Token Index: 664