Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 67 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1327785 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1187335 (The Pile)

Max Activating Token Index: 801

Text #2

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1472974 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1892254 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1942440 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1446599 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1675507 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2451. Min Act: -0.0000

Data Index: 50171 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2358. Min Act: -0.0000

Data Index: 375287 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2400. Min Act: -0.0000

Data Index: 506224 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2075. Min Act: -0.0000

Data Index: 919374 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1729180 (The Pile)

Max Activating Token Index: 771

Text #12

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1677247 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2103. Min Act: -0.0000

Data Index: 214885 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1428247 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2172. Min Act: -0.0000

Data Index: 226501 (The Pile)

Max Activating Token Index: 727

Text #16

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2208. Min Act: -0.0000

Data Index: 106943 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1931516 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1761048 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1873548 (The Pile)

Max Activating Token Index: 784