Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2020 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0006

Data Index: 891489 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0151. Min Act: -0.0006

Data Index: 994471 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0136. Min Act: -0.0006

Data Index: 138942 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0136. Min Act: -0.0006

Data Index: 873321 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0129. Min Act: -0.0006

Data Index: 713512 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0131. Min Act: -0.0006

Data Index: 237850 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0134. Min Act: -0.0006

Data Index: 496581 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0129. Min Act: -0.0006

Data Index: 78530 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0118. Min Act: -0.0006

Data Index: 192071 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1082047 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0119. Min Act: -0.0006

Data Index: 568057 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0125. Min Act: -0.0006

Data Index: 430588 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0121. Min Act: -0.0006

Data Index: 521876 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0112. Min Act: -0.0006

Data Index: 565392 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0115. Min Act: -0.0006

Data Index: 837698 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0120. Min Act: -0.0006

Data Index: 824881 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1233173 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0118. Min Act: -0.0006

Data Index: 729910 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0121. Min Act: -0.0006

Data Index: 996941 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1168595 (C4 (Web Text))

Max Activating Token Index: 725