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

Dataset: The Pile

Neuron 1449 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: 1.8036. Min Range: -1.8036

Max Act: 1.8036. Min Act: -0.0000

Data Index: 216749 (The Pile)

Max Activating Token Index: 261

Text #1

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.6010. Min Act: -0.0000

Data Index: 1852871 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.5203. Min Act: -0.0000

Data Index: 1866796 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.5051. Min Act: -0.0000

Data Index: 194181 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1978551 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2339. Min Act: -0.0000

Data Index: 10652 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.3845. Min Act: -0.0000

Data Index: 1201131 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2883. Min Act: -0.0000

Data Index: 563249 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2357. Min Act: -0.0000

Data Index: 63596 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2964. Min Act: -0.0000

Data Index: 1674513 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1234459 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.3231. Min Act: -0.0000

Data Index: 661025 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1887952 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1511199 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1121221 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 1.8036. Min Range: -1.8036

Max Act: 0.9552. Min Act: -0.0000

Data Index: 592186 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1425. Min Act: -0.0000

Data Index: 301198 (The Pile)

Max Activating Token Index: 75

Text #17

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.1364. Min Act: -0.0000

Data Index: 219046 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.0122. Min Act: -0.0000

Data Index: 731684 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 1.8036. Min Range: -1.8036

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1290925 (The Pile)

Max Activating Token Index: 194