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

Dataset: The Pile

Neuron 2272 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1236032 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1729314 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1343737 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.3530. Min Act: -0.0000

Data Index: 478266 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.2440. Min Act: -0.0000

Data Index: 835630 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1897585 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1727671 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.3051. Min Act: -0.0000

Data Index: 578082 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1583311 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1139955 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.3416. Min Act: -0.0000

Data Index: 1542231 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.2329. Min Act: -0.0000

Data Index: 967689 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.1095. Min Act: -0.0000

Data Index: 259935 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1408554 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.2628. Min Act: -0.0000

Data Index: 438771 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.2181. Min Act: -0.0000

Data Index: 322452 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.2144. Min Act: -0.0000

Data Index: 887366 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1247858 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1146640 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 1.4107. Min Range: -1.4107

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1389001 (The Pile)

Max Activating Token Index: 231