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

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

Neuron 815 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0006

Data Index: 583623 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0145. Min Act: -0.0005

Data Index: 138306 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0143. Min Act: -0.0006

Data Index: 827142 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0136. Min Act: -0.0004

Data Index: 1622234 (Python Code)

Max Activating Token Index: 246

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0139. Min Act: -0.0006

Data Index: 682342 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1571143 (Python Code)

Max Activating Token Index: 317

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0131. Min Act: -0.0006

Data Index: 62229 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0130. Min Act: -0.0005

Data Index: 268853 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0133. Min Act: -0.0006

Data Index: 59024 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1423384 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1305916 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0132. Min Act: -0.0006

Data Index: 400648 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1057065 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1622007 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0133. Min Act: -0.0006

Data Index: 989251 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0126. Min Act: -0.0006

Data Index: 370844 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0126. Min Act: -0.0004

Data Index: 1414799 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1060066 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0130. Min Act: -0.0006

Data Index: 829798 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1442956 (Python Code)

Max Activating Token Index: 250