Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1094977 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1018507 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0672. Min Act: -0.0001

Data Index: 914810 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0668. Min Act: -0.0001

Data Index: 110467 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1113222 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1063281 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1608245 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0669. Min Act: -0.0001

Data Index: 82679 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1219055 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1073637 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0585. Min Act: -0.0001

Data Index: 726224 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0610. Min Act: -0.0000

Data Index: 350802 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1123946 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1174289 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0614. Min Act: -0.0001

Data Index: 866522 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0591. Min Act: -0.0001

Data Index: 879309 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1140429 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0548. Min Act: -0.0001

Data Index: 586349 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0542. Min Act: -0.0001

Data Index: 66704 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.0713. Min Range: -0.0713

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1347346 (C4 (Web Text))

Max Activating Token Index: 857