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

Dataset: The Pile

Neuron 3628 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.2163. Min Act: -0.0000

Data Index: 359238 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1801545 (The Pile)

Max Activating Token Index: 243

Text #2

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9044. Min Act: -0.0000

Data Index: 300435 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1227523 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1963239 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8642. Min Act: -0.0000

Data Index: 424004 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9359. Min Act: -0.0000

Data Index: 253936 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8438. Min Act: -0.0000

Data Index: 986168 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1297074 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8320. Min Act: -0.0000

Data Index: 74876 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1039505 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8925. Min Act: -0.0000

Data Index: 537141 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8641. Min Act: -0.0000

Data Index: 606910 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8245. Min Act: -0.0000

Data Index: 34703 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.7555. Min Act: -0.0000

Data Index: 467757 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1502490 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1474595 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1821990 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8027. Min Act: -0.0000

Data Index: 229692 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1094035 (The Pile)

Max Activating Token Index: 820