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

Dataset: The Pile

Neuron 4841 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: 1.1469. Min Range: -1.1469

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1240452 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0744. Min Act: -0.0000

Data Index: 234823 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0936. Min Act: -0.0000

Data Index: 1043863 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0185. Min Act: -0.0000

Data Index: 133696 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1719317 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9006. Min Act: -0.0000

Data Index: 763972 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1142020 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8821. Min Act: -0.0000

Data Index: 290332 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8509. Min Act: -0.0000

Data Index: 911779 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1582760 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1448925 (The Pile)

Max Activating Token Index: 917

Text #11

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7782. Min Act: -0.0000

Data Index: 188933 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8866. Min Act: -0.0000

Data Index: 806038 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1747048 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1078647 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8402. Min Act: -0.0000

Data Index: 82280 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8095. Min Act: -0.0000

Data Index: 367465 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1825896 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1570053 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8021. Min Act: -0.0000

Data Index: 495968 (The Pile)

Max Activating Token Index: 149