Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1451 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1572509 (Python Code)

Max Activating Token Index: 94

Text #1

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1602938 (Python Code)

Max Activating Token Index: 487

Text #2

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1501068 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1186. Min Act: -0.0001

Data Index: 671929 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1162. Min Act: -0.0001

Data Index: 505311 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1431457 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1642261 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1026199 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1494613 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1119. Min Act: -0.0002

Data Index: 346173 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1152. Min Act: -0.0002

Data Index: 598181 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1615097 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1369291 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1596164 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1587605 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1605853 (Python Code)

Max Activating Token Index: 745

Text #16

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1003093 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1407889 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1416479 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1557395 (Python Code)

Max Activating Token Index: 140