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

Dataset: The Pile

Neuron 1226 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0742. Min Range: -3.0742

Max Act: 3.0742. Min Act: -0.0000

Data Index: 1177080 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.8150. Min Act: -0.0000

Data Index: 277278 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 3.0742. Min Range: -3.0742

Max Act: 3.0015. Min Act: -0.0000

Data Index: 738879 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.5023. Min Act: -0.0000

Data Index: 1535388 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.4675. Min Act: -0.0000

Data Index: 1718811 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.3850. Min Act: -0.0000

Data Index: 1098551 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.6909. Min Act: -0.0000

Data Index: 263853 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.3273. Min Act: -0.0000

Data Index: 1102412 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.0299. Min Act: -0.0000

Data Index: 1634435 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.2907. Min Act: -0.0000

Data Index: 1583301 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.1866. Min Act: -0.0000

Data Index: 1351292 (The Pile)

Max Activating Token Index: 943

Text #11

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.5731. Min Act: -0.0000

Data Index: 974437 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 3.0742. Min Range: -3.0742

Max Act: 1.9319. Min Act: -0.0000

Data Index: 183027 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.3612. Min Act: -0.0000

Data Index: 1963107 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.3665. Min Act: -0.0000

Data Index: 1778375 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.1522. Min Act: -0.0000

Data Index: 302543 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.3177. Min Act: -0.0000

Data Index: 192528 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.1304. Min Act: -0.0000

Data Index: 1591376 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.0049. Min Act: -0.0000

Data Index: 514370 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 3.0742. Min Range: -3.0742

Max Act: 2.2165. Min Act: -0.0000

Data Index: 1393402 (The Pile)

Max Activating Token Index: 239