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

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

Neuron 3373 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3899. Min Act: -0.0000

Data Index: 791115 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1061620 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2561. Min Act: -0.0000

Data Index: 779997 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3652. Min Act: -0.0000

Data Index: 960417 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2827. Min Act: -0.0000

Data Index: 372175 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2636. Min Act: -0.0000

Data Index: 262628 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3243. Min Act: -0.0000

Data Index: 589161 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2478. Min Act: -0.0000

Data Index: 1329553 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1889. Min Act: -0.0000

Data Index: 845205 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1767. Min Act: -0.0000

Data Index: 547549 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1194. Min Act: -0.0000

Data Index: 140055 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0098. Min Act: -0.0000

Data Index: 470961 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0360. Min Act: -0.0000

Data Index: 941209 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0454. Min Act: -0.0000

Data Index: 881473 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.0371. Min Act: -0.0000

Data Index: 1162255 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.3899. Min Range: -1.3899

Max Act: 0.8852. Min Act: -0.0000

Data Index: 964204 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.3899. Min Range: -1.3899

Max Act: 0.9342. Min Act: -0.0000

Data Index: 560461 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 1.3899. Min Range: -1.3899

Max Act: 0.9046. Min Act: -0.0000

Data Index: 430362 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.3899. Min Range: -1.3899

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1274420 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 1.3899. Min Range: -1.3899

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1124267 (C4 (Web Text))

Max Activating Token Index: 475