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

Dataset: The Pile

Neuron 3262 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 6.1510. Min Range: -6.1510

Max Act: 6.1510. Min Act: -0.0000

Data Index: 1107447 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 6.1510. Min Range: -6.1510

Max Act: 5.2999. Min Act: -0.0000

Data Index: 494658 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 6.1510. Min Range: -6.1510

Max Act: 5.1147. Min Act: -0.0000

Data Index: 1408297 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 6.1510. Min Range: -6.1510

Max Act: 5.1202. Min Act: -0.0000

Data Index: 422093 (The Pile)

Max Activating Token Index: 656

Text #4

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.9133. Min Act: -0.0000

Data Index: 511188 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 6.1510. Min Range: -6.1510

Max Act: 5.5115. Min Act: -0.0000

Data Index: 1804733 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.6191. Min Act: -0.0000

Data Index: 433033 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 6.1510. Min Range: -6.1510

Max Act: 5.1086. Min Act: -0.0000

Data Index: 1135733 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 6.1510. Min Range: -6.1510

Max Act: 4.8242. Min Act: -0.0000

Data Index: 1453157 (The Pile)

Max Activating Token Index: 683

Text #9

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.2452. Min Act: -0.0000

Data Index: 1308994 (The Pile)

Max Activating Token Index: 534

Text #10

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.6926. Min Act: -0.0000

Data Index: 1084053 (The Pile)

Max Activating Token Index: 626

Text #11

Max Range: 6.1510. Min Range: -6.1510

Max Act: 4.0276. Min Act: -0.0000

Data Index: 528109 (The Pile)

Max Activating Token Index: 884

Text #12

Max Range: 6.1510. Min Range: -6.1510

Max Act: 5.0625. Min Act: -0.0000

Data Index: 1431904 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.6209. Min Act: -0.0000

Data Index: 349307 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.9177. Min Act: -0.0000

Data Index: 2355 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.2641. Min Act: -0.0000

Data Index: 1538188 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 6.1510. Min Range: -6.1510

Max Act: 2.6536. Min Act: -0.0000

Data Index: 1439322 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.5255. Min Act: -0.0000

Data Index: 1155670 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 6.1510. Min Range: -6.1510

Max Act: 4.2235. Min Act: -0.0000

Data Index: 1206729 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 6.1510. Min Range: -6.1510

Max Act: 3.8293. Min Act: -0.0000

Data Index: 1710159 (The Pile)

Max Activating Token Index: 430