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

Dataset: The Pile

Neuron 501 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: 0.2549. Min Range: -0.2549

Max Act: 0.2549. Min Act: -0.0000

Data Index: 940480 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1325773 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2428. Min Act: -0.0000

Data Index: 644771 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2185. Min Act: -0.0000

Data Index: 852214 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1216189 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1938083 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1006958 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1214826 (The Pile)

Max Activating Token Index: 857

Text #8

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1699139 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1134308 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2020. Min Act: -0.0000

Data Index: 825403 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1921023 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1932. Min Act: -0.0000

Data Index: 213538 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1165578 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1896. Min Act: -0.0000

Data Index: 509931 (The Pile)

Max Activating Token Index: 788

Text #15

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1154481 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1765033 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1874450 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1959. Min Act: -0.0000

Data Index: 386764 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1140156 (The Pile)

Max Activating Token Index: 867