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

Dataset: The Pile

Neuron 3942 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2096. Min Act: -0.0000

Data Index: 726686 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1679160 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1437027 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2016. Min Act: -0.0000

Data Index: 205064 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2118. Min Act: -0.0000

Data Index: 630812 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1263676 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1825265 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2172. Min Act: -0.0000

Data Index: 643803 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1094527 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1997. Min Act: -0.0000

Data Index: 971838 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1849271 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1916. Min Act: -0.0000

Data Index: 526116 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1397281 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1875322 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1638254 (The Pile)

Max Activating Token Index: 18

Text #15

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1829. Min Act: -0.0000

Data Index: 894298 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1397310 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1149614 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1430181 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 0.2590. Min Range: -0.2590

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1928761 (The Pile)

Max Activating Token Index: 979