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

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

Neuron 1324 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0005

Data Index: 1034041 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0120. Min Act: -0.0005

Data Index: 882374 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0182. Min Act: -0.0005

Data Index: 981659 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0148. Min Act: -0.0004

Data Index: 306890 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0162. Min Act: -0.0004

Data Index: 715189 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0174. Min Act: -0.0004

Data Index: 247581 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0178. Min Act: -0.0005

Data Index: 1238519 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0127. Min Act: -0.0004

Data Index: 942526 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0132. Min Act: -0.0004

Data Index: 330852 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0200. Min Act: -0.0005

Data Index: 855079 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0131. Min Act: -0.0005

Data Index: 188882 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0111. Min Act: -0.0004

Data Index: 82087 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1330886 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0155. Min Act: -0.0005

Data Index: 549702 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0127. Min Act: -0.0005

Data Index: 313641 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0134. Min Act: -0.0005

Data Index: 1271925 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0125. Min Act: -0.0004

Data Index: 906131 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0142. Min Act: -0.0005

Data Index: 238822 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0113. Min Act: -0.0004

Data Index: 907705 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0125. Min Act: -0.0004

Data Index: 625945 (C4 (Web Text))

Max Activating Token Index: 172