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

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

Neuron 5788 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8917. Min Act: -0.0000

Data Index: 138750 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8713. Min Act: -0.0000

Data Index: 905474 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7187. Min Act: -0.0000

Data Index: 38029 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6648. Min Act: -0.0000

Data Index: 361794 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1001929 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6732. Min Act: -0.0000

Data Index: 255894 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7192. Min Act: -0.0000

Data Index: 546238 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7213. Min Act: -0.0000

Data Index: 511591 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6647. Min Act: -0.0000

Data Index: 47698 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6444. Min Act: -0.0000

Data Index: 165968 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1180537 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6604. Min Act: -0.0000

Data Index: 780361 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6405. Min Act: -0.0000

Data Index: 230098 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1313663 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6545. Min Act: -0.0000

Data Index: 654770 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6927. Min Act: -0.0000

Data Index: 158586 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6160. Min Act: -0.0000

Data Index: 383801 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6128. Min Act: -0.0000

Data Index: 971473 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6595. Min Act: -0.0000

Data Index: 694199 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1110069 (C4 (Web Text))

Max Activating Token Index: 359