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

Dataset: The Pile

Neuron 3433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.1144. Min Act: -0.0000

Data Index: 787182 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1656722 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.0702. Min Act: -0.0000

Data Index: 170976 (The Pile)

Max Activating Token Index: 315

Text #3

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1848829 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.0327. Min Act: -0.0000

Data Index: 62352 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.0363. Min Act: -0.0000

Data Index: 72273 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 1.1677. Min Range: -1.1677

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1308875 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1334335 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9998. Min Act: -0.0000

Data Index: 930738 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1488352 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1724567 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1970707 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1968510 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1747981 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8460. Min Act: -0.0000

Data Index: 193943 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1301176 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8465. Min Act: -0.0000

Data Index: 871261 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8602. Min Act: -0.0000

Data Index: 23250 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1278253 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 1.1677. Min Range: -1.1677

Max Act: 0.8339. Min Act: -0.0000

Data Index: 511306 (The Pile)

Max Activating Token Index: 516