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

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

Neuron 937 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: 0.0154. Min Range: -0.0154

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1229928 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0146. Min Act: -0.0006

Data Index: 421118 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0144. Min Act: -0.0006

Data Index: 416434 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1119284 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1106954 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0137. Min Act: -0.0006

Data Index: 851509 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1262415 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1154638 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1304707 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0139. Min Act: -0.0006

Data Index: 810647 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1043288 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0123. Min Act: -0.0006

Data Index: 911388 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0124. Min Act: -0.0006

Data Index: 396232 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0133. Min Act: -0.0006

Data Index: 229237 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1128081 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0132. Min Act: -0.0006

Data Index: 910414 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0122. Min Act: -0.0006

Data Index: 164481 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0122. Min Act: -0.0006

Data Index: 787240 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0127. Min Act: -0.0006

Data Index: 341168 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1081950 (C4 (Web Text))

Max Activating Token Index: 178