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

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

Neuron 2191 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.2981. Min Act: -0.0000

Data Index: 576834 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1084607 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1253048 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9661. Min Act: 0.0000

Data Index: 12245 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1250491 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9212. Min Act: -0.0000

Data Index: 65761 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1075423 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9037. Min Act: -0.0000

Data Index: 208626 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8771. Min Act: -0.0000

Data Index: 789948 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1271020 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8236. Min Act: -0.0000

Data Index: 55614 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8445. Min Act: -0.0000

Data Index: 377695 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8540. Min Act: -0.0000

Data Index: 947019 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8711. Min Act: -0.0000

Data Index: 651100 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8157. Min Act: -0.0000

Data Index: 294485 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8396. Min Act: -0.0000

Data Index: 811818 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8392. Min Act: -0.0000

Data Index: 142692 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8852. Min Act: -0.0000

Data Index: 669193 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1261578 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.7958. Min Act: -0.0000

Data Index: 747592 (C4 (Web Text))

Max Activating Token Index: 875