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

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

Neuron 1964 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7626. Min Act: -0.0000

Data Index: 121270 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6756. Min Act: -0.0000

Data Index: 363533 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6438. Min Act: -0.0000

Data Index: 277947 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1217980 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6613. Min Act: -0.0001

Data Index: 62981 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6499. Min Act: -0.0000

Data Index: 500796 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6268. Min Act: -0.0000

Data Index: 71997 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1239249 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6213. Min Act: 0.0000

Data Index: 1025105 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5595. Min Act: -0.0000

Data Index: 447618 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5829. Min Act: -0.0000

Data Index: 333709 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1221104 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1250737 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5741. Min Act: -0.0000

Data Index: 17543 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1235498 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1277059 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5843. Min Act: -0.0000

Data Index: 502831 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5828. Min Act: -0.0000

Data Index: 635736 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1332566 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1143507 (C4 (Web Text))

Max Activating Token Index: 984