Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 477 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.9221. Min Act: -0.0001

Data Index: 391282 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8915. Min Act: -0.0001

Data Index: 1051579 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8446. Min Act: -0.0001

Data Index: 1036104 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8501. Min Act: -0.0001

Data Index: 338115 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8349. Min Act: -0.0001

Data Index: 275276 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8246. Min Act: -0.0001

Data Index: 394034 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8179. Min Act: -0.0001

Data Index: 1057612 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8146. Min Act: -0.0001

Data Index: 184108 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8013. Min Act: -0.0001

Data Index: 346218 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1579978 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.8250. Min Act: -0.0001

Data Index: 787979 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7858. Min Act: -0.0001

Data Index: 281349 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7539. Min Act: -0.0001

Data Index: 398854 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7559. Min Act: -0.0001

Data Index: 1190758 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7717. Min Act: -0.0001

Data Index: 254178 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7656. Min Act: -0.0001

Data Index: 76078 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.6867. Min Act: -0.0001

Data Index: 1289712 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.7076. Min Act: -0.0001

Data Index: 665314 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.6633. Min Act: -0.0001

Data Index: 243888 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.9221. Min Range: -0.9221

Max Act: 0.6958. Min Act: -0.0001

Data Index: 513473 (C4 (Web Text))

Max Activating Token Index: 456