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

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

Neuron 4787 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.9986. Min Act: -0.0000

Data Index: 1197835 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.6291. Min Act: -0.0000

Data Index: 490137 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.6047. Min Act: -0.0000

Data Index: 481110 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1617531 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5788. Min Act: -0.0000

Data Index: 329631 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5944. Min Act: 0.0000

Data Index: 1519595 (Python Code)

Max Activating Token Index: 542

Text #6

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5747. Min Act: -0.0000

Data Index: 912486 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5725. Min Act: 0.0000

Data Index: 1000369 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.6018. Min Act: -0.0000

Data Index: 300240 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5460. Min Act: -0.0000

Data Index: 799621 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5275. Min Act: -0.0000

Data Index: 96881 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1521772 (Python Code)

Max Activating Token Index: 126

Text #12

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1126374 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5032. Min Act: -0.0000

Data Index: 76513 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1407612 (Python Code)

Max Activating Token Index: 887

Text #15

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1499036 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.4821. Min Act: 0.0000

Data Index: 425856 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.4891. Min Act: 0.0000

Data Index: 443333 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.4997. Min Act: -0.0000

Data Index: 206466 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.9986. Min Range: -0.9986

Max Act: 0.5188. Min Act: 0.0001

Data Index: 644425 (C4 (Web Text))

Max Activating Token Index: 328