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

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

Neuron 3650 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.8440. Min Act: -0.0000

Data Index: 37757 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.7082. Min Act: -0.0000

Data Index: 414 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6356. Min Act: 0.0000

Data Index: 593791 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1036363 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6833. Min Act: -0.0000

Data Index: 878671 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6260. Min Act: -0.0000

Data Index: 699120 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6091. Min Act: 0.0000

Data Index: 109051 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5541. Min Act: -0.0000

Data Index: 615837 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6067. Min Act: -0.0000

Data Index: 520472 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1217430 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5829. Min Act: -0.0000

Data Index: 379042 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5917. Min Act: -0.0000

Data Index: 476505 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5968. Min Act: -0.0000

Data Index: 994091 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5687. Min Act: 0.0000

Data Index: 73178 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.6018. Min Act: -0.0000

Data Index: 241502 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5952. Min Act: 0.0001

Data Index: 417060 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5918. Min Act: -0.0000

Data Index: 217957 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1155692 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5528. Min Act: -0.0000

Data Index: 420445 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.8440. Min Range: -0.8440

Max Act: 0.5864. Min Act: -0.0000

Data Index: 326050 (C4 (Web Text))

Max Activating Token Index: 457