Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4475 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1210970 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0002

Data Index: 466892 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0131. Min Act: -0.0002

Data Index: 797863 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1348356 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0125. Min Act: -0.0002

Data Index: 553077 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0124. Min Act: -0.0002

Data Index: 418778 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0122. Min Act: -0.0002

Data Index: 745741 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1072943 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0122. Min Act: -0.0002

Data Index: 729628 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0122. Min Act: -0.0002

Data Index: 557712 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0121. Min Act: -0.0002

Data Index: 398775 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1211436 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1331403 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0116. Min Act: -0.0002

Data Index: 172953 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0118. Min Act: -0.0002

Data Index: 689631 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0116. Min Act: -0.0002

Data Index: 654272 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0117. Min Act: -0.0002

Data Index: 807295 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0118. Min Act: -0.0002

Data Index: 341253 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0117. Min Act: -0.0002

Data Index: 874448 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0115. Min Act: -0.0002

Data Index: 729995 (C4 (Web Text))

Max Activating Token Index: 673