Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5517 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1385591 (Python Code)

Max Activating Token Index: 296

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0122. Min Act: -0.0002

Data Index: 109387 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0002

Data Index: 412963 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0120. Min Act: -0.0002

Data Index: 498625 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1219187 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1374976 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1058935 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1096995 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0108. Min Act: -0.0002

Data Index: 1108747 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0111. Min Act: -0.0002

Data Index: 94281 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0109. Min Act: -0.0002

Data Index: 414955 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1455107 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1142910 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0002

Data Index: 9566 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1610936 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0106. Min Act: -0.0002

Data Index: 862262 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0102. Min Act: -0.0002

Data Index: 688790 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1370507 (Python Code)

Max Activating Token Index: 474

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0111. Min Act: -0.0002

Data Index: 95080 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1362546 (Python Code)

Max Activating Token Index: 8