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

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

Neuron 1430 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: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0005

Data Index: 631844 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0005

Data Index: 637009 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0005

Data Index: 1269914 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0006

Data Index: 600151 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0005

Data Index: 256923 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0005

Data Index: 1265459 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0005

Data Index: 1054012 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0005

Data Index: 530013 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0005

Data Index: 408401 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0005

Data Index: 721046 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0005

Data Index: 997483 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0144. Min Act: -0.0005

Data Index: 385266 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0006

Data Index: 545388 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0005

Data Index: 232322 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0143. Min Act: -0.0005

Data Index: 224030 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0143. Min Act: -0.0005

Data Index: 1257365 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0005

Data Index: 619760 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0005

Data Index: 859424 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0005

Data Index: 36790 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1203294 (C4 (Web Text))

Max Activating Token Index: 922