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

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

Neuron 641 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: 0.0142. Min Range: -0.0142

Max Act: 0.0139. Min Act: -0.0006

Data Index: 788751 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1312168 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0132. Min Act: -0.0006

Data Index: 388193 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0137. Min Act: -0.0006

Data Index: 613832 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1153847 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0142. Min Act: -0.0006

Data Index: 269313 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1000130 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0137. Min Act: -0.0006

Data Index: 489141 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0138. Min Act: -0.0006

Data Index: 346154 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1192089 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1305549 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0128. Min Act: -0.0006

Data Index: 568496 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0129. Min Act: -0.0006

Data Index: 794290 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0131. Min Act: -0.0006

Data Index: 38449 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0138. Min Act: -0.0006

Data Index: 975748 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0124. Min Act: -0.0006

Data Index: 618125 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1179816 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0128. Min Act: -0.0006

Data Index: 223398 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1084100 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0124. Min Act: -0.0006

Data Index: 213679 (C4 (Web Text))

Max Activating Token Index: 504