Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1878 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0132. Min Act: -0.0005

Data Index: 685301 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0130. Min Act: -0.0005

Data Index: 167774 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0128. Min Act: -0.0005

Data Index: 869192 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1484158 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0005

Data Index: 496957 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1007763 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1343077 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1185435 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1559841 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0108. Min Act: -0.0005

Data Index: 745438 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0107. Min Act: -0.0005

Data Index: 93504 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0107. Min Act: -0.0005

Data Index: 22862 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0106. Min Act: -0.0005

Data Index: 639454 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0104. Min Act: -0.0005

Data Index: 380366 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0105. Min Act: -0.0005

Data Index: 284999 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0103. Min Act: -0.0005

Data Index: 60137 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0103. Min Act: -0.0005

Data Index: 10625 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1230911 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0103. Min Act: -0.0005

Data Index: 146266 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0103. Min Act: -0.0005

Data Index: 206146 (C4 (Web Text))

Max Activating Token Index: 241