Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 510 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0160. Min Act: -0.0005

Data Index: 106298 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0158. Min Act: -0.0004

Data Index: 223091 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0147. Min Act: -0.0005

Data Index: 899840 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0149. Min Act: -0.0004

Data Index: 622093 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0142. Min Act: -0.0005

Data Index: 186977 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0144. Min Act: -0.0005

Data Index: 141561 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0144. Min Act: -0.0004

Data Index: 28330 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0143. Min Act: -0.0004

Data Index: 1200004 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0142. Min Act: -0.0005

Data Index: 860421 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0142. Min Act: -0.0005

Data Index: 760040 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0142. Min Act: -0.0004

Data Index: 311291 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0142. Min Act: -0.0004

Data Index: 875999 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0141. Min Act: -0.0004

Data Index: 322629 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0140. Min Act: -0.0004

Data Index: 1177315 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0139. Min Act: -0.0004

Data Index: 463657 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1295677 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0139. Min Act: -0.0004

Data Index: 558313 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0138. Min Act: -0.0005

Data Index: 229667 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0138. Min Act: -0.0005

Data Index: 798274 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0135. Min Act: -0.0004

Data Index: 968848 (C4 (Web Text))

Max Activating Token Index: 253