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

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

Neuron 17 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: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0005

Data Index: 966127 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1061470 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0005

Data Index: 1016058 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0131. Min Act: -0.0005

Data Index: 1325810 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1316648 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0005

Data Index: 727248 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1176211 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0005

Data Index: 388179 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1346389 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1242839 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0005

Data Index: 660974 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1344324 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0124. Min Act: -0.0005

Data Index: 573461 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0124. Min Act: -0.0005

Data Index: 288662 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0005

Data Index: 575126 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0121. Min Act: -0.0005

Data Index: 350423 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0123. Min Act: -0.0005

Data Index: 1084144 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0005

Data Index: 505434 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0120. Min Act: -0.0005

Data Index: 707610 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1180781 (C4 (Web Text))

Max Activating Token Index: 92