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

Dataset: The Pile

Neuron 4777 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: 1.2336. Min Range: -1.2336

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1010305 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1500. Min Act: -0.0000

Data Index: 789263 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1205104 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1193959 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.0914. Min Act: -0.0000

Data Index: 669244 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1668272 (The Pile)

Max Activating Token Index: 777

Text #6

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1452860 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1771039 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1077126 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8553. Min Act: -0.0000

Data Index: 954395 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1669743 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8519. Min Act: -0.0000

Data Index: 83821 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1091203 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1697783 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.7980. Min Act: -0.0000

Data Index: 245220 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1848321 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.7977. Min Act: -0.0000

Data Index: 316101 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1734318 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8198. Min Act: -0.0000

Data Index: 178675 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1188980 (The Pile)

Max Activating Token Index: 436