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

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

Neuron 1224 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.3531. Min Act: -0.0000

Data Index: 246487 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.3245. Min Act: -0.0000

Data Index: 78798 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2750. Min Act: -0.0000

Data Index: 558194 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2803. Min Act: -0.0000

Data Index: 912983 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2967. Min Act: -0.0000

Data Index: 295988 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2836. Min Act: -0.0000

Data Index: 556607 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2970. Min Act: -0.0000

Data Index: 99198 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2413. Min Act: -0.0000

Data Index: 905221 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2845. Min Act: -0.0000

Data Index: 189585 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2509. Min Act: -0.0000

Data Index: 171225 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2323. Min Act: -0.0000

Data Index: 406102 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1243204 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2617. Min Act: -0.0000

Data Index: 45598 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2741. Min Act: -0.0000

Data Index: 628175 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1048842 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2603. Min Act: -0.0000

Data Index: 504442 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2667. Min Act: -0.0000

Data Index: 736254 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1165716 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2474. Min Act: -0.0000

Data Index: 131234 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.3531. Min Range: -0.3531

Max Act: 0.2557. Min Act: -0.0000

Data Index: 120984 (C4 (Web Text))

Max Activating Token Index: 614