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

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

Neuron 964 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0174. Min Act: -0.0005

Data Index: 53435 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0154. Min Act: -0.0005

Data Index: 573802 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0153. Min Act: -0.0005

Data Index: 257359 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0151. Min Act: -0.0005

Data Index: 348844 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0147. Min Act: -0.0005

Data Index: 580669 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0144. Min Act: -0.0005

Data Index: 370439 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0153. Min Act: -0.0005

Data Index: 1099063 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0152. Min Act: -0.0005

Data Index: 1082007 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0144. Min Act: -0.0005

Data Index: 835718 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0143. Min Act: -0.0005

Data Index: 1517587 (Python Code)

Max Activating Token Index: 384

Text #10

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0150. Min Act: -0.0005

Data Index: 1314423 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1190354 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0141. Min Act: -0.0005

Data Index: 885431 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0149. Min Act: -0.0005

Data Index: 102304 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1169013 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0136. Min Act: -0.0005

Data Index: 920973 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1386461 (Python Code)

Max Activating Token Index: 385

Text #17

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0131. Min Act: -0.0005

Data Index: 1447799 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0145. Min Act: -0.0005

Data Index: 979901 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.0174. Min Range: -0.0174

Max Act: 0.0138. Min Act: -0.0005

Data Index: 1442018 (Python Code)

Max Activating Token Index: 11