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

Dataset: The Pile

Neuron 1301 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.7275. Min Act: -0.0000

Data Index: 474114 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.5286. Min Act: -0.0000

Data Index: 84737 (The Pile)

Max Activating Token Index: 911

Text #2

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4601. Min Act: -0.0000

Data Index: 405387 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1836973 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.5140. Min Act: -0.0000

Data Index: 684871 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1709421 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3612. Min Act: -0.0000

Data Index: 552064 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.5252. Min Act: -0.0000

Data Index: 324251 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.5208. Min Act: -0.0000

Data Index: 140833 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3207. Min Act: -0.0000

Data Index: 1914510 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1281300 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3065. Min Act: -0.0000

Data Index: 661834 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3005. Min Act: -0.0000

Data Index: 982831 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3585. Min Act: -0.0000

Data Index: 494584 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.1484. Min Act: -0.0000

Data Index: 191367 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1262386 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.1448. Min Act: -0.0000

Data Index: 1450275 (The Pile)

Max Activating Token Index: 812

Text #17

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.2183. Min Act: -0.0000

Data Index: 1859271 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1248538 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 1.7275. Min Range: -1.7275

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1658190 (The Pile)

Max Activating Token Index: 736