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

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

Neuron 956 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9272. Min Act: -0.0000

Data Index: 1395797 (Python Code)

Max Activating Token Index: 462

Text #1

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9917. Min Act: -0.0000

Data Index: 1466193 (Python Code)

Max Activating Token Index: 896

Text #2

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9413. Min Act: -0.0000

Data Index: 812430 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.5567. Min Act: -0.0000

Data Index: 1489974 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.6227. Min Act: -0.0000

Data Index: 1485187 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.5646. Min Act: -0.0001

Data Index: 1523436 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1545725 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.4535. Min Act: -0.0001

Data Index: 1385684 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1553502 (Python Code)

Max Activating Token Index: 962

Text #9

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.4922. Min Act: -0.0000

Data Index: 1003780 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3984. Min Act: -0.0000

Data Index: 86685 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1546614 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.4725. Min Act: -0.0001

Data Index: 1656715 (Python Code)

Max Activating Token Index: 621

Text #13

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1166990 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1513102 (Python Code)

Max Activating Token Index: 167

Text #15

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.5202. Min Act: -0.0000

Data Index: 530038 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2842. Min Act: -0.0000

Data Index: 1084134 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3705. Min Act: -0.0000

Data Index: 1161031 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.4244. Min Act: -0.0000

Data Index: 785302 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3745. Min Act: -0.0000

Data Index: 1108879 (C4 (Web Text))

Max Activating Token Index: 705