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

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

Neuron 708 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: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0006

Data Index: 229046 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1344297 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1384873 (Python Code)

Max Activating Token Index: 633

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0152. Min Act: -0.0006

Data Index: 760540 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0139. Min Act: -0.0006

Data Index: 822688 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1597291 (Python Code)

Max Activating Token Index: 543

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0137. Min Act: -0.0007

Data Index: 964022 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0132. Min Act: -0.0006

Data Index: 674785 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0134. Min Act: -0.0006

Data Index: 978011 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1182371 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1165854 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0131. Min Act: -0.0006

Data Index: 101116 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0133. Min Act: -0.0006

Data Index: 713764 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0130. Min Act: -0.0006

Data Index: 855186 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0130. Min Act: -0.0006

Data Index: 604781 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1034987 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1564138 (Python Code)

Max Activating Token Index: 426

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1268773 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0124. Min Act: -0.0006

Data Index: 40807 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1263685 (C4 (Web Text))

Max Activating Token Index: 791