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

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

Neuron 1313 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1521930 (Python Code)

Max Activating Token Index: 641

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0173. Min Act: -0.0006

Data Index: 628225 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0155. Min Act: -0.0006

Data Index: 770114 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0139. Min Act: -0.0006

Data Index: 168744 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0127. Min Act: -0.0006

Data Index: 644989 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0131. Min Act: -0.0006

Data Index: 344965 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0134. Min Act: -0.0005

Data Index: 1647831 (Python Code)

Max Activating Token Index: 692

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1248705 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0118. Min Act: -0.0006

Data Index: 315817 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0126. Min Act: -0.0006

Data Index: 330346 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0128. Min Act: -0.0006

Data Index: 289308 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0123. Min Act: -0.0006

Data Index: 16043 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0114. Min Act: -0.0006

Data Index: 770600 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0117. Min Act: -0.0006

Data Index: 237665 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0128. Min Act: -0.0006

Data Index: 565760 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0116. Min Act: -0.0006

Data Index: 129660 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0107. Min Act: -0.0006

Data Index: 660900 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0112. Min Act: -0.0006

Data Index: 977910 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0116. Min Act: -0.0006

Data Index: 774358 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0115. Min Act: -0.0006

Data Index: 668758 (C4 (Web Text))

Max Activating Token Index: 983