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

Dataset: The Pile

Neuron 5108 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.4860. Min Act: -0.0000

Data Index: 154820 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.3894. Min Act: -0.0000

Data Index: 546138 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.3593. Min Act: -0.0000

Data Index: 92548 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2402. Min Act: -0.0000

Data Index: 160432 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1771061 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2994. Min Act: -0.0000

Data Index: 8232 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2969. Min Act: -0.0000

Data Index: 1875280 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1750056 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1356060 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1782. Min Act: -0.0000

Data Index: 124909 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1068503 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2344. Min Act: -0.0000

Data Index: 813884 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1059151 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1169100 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1720. Min Act: -0.0000

Data Index: 586704 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1990501 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2096. Min Act: -0.0000

Data Index: 102193 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1540032 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1210959 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 1.4860. Min Range: -1.4860

Max Act: 1.2280. Min Act: -0.0000

Data Index: 369444 (The Pile)

Max Activating Token Index: 331