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

Dataset: The Pile

Neuron 2790 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.1377. Min Act: -0.0000

Data Index: 326082 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.3434. Min Act: -0.0000

Data Index: 7323 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.2336. Min Act: -0.0000

Data Index: 579297 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.2271. Min Act: -0.0000

Data Index: 1925159 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1509069 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.2258. Min Act: -0.0000

Data Index: 221219 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9661. Min Act: -0.0000

Data Index: 802485 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0888. Min Act: -0.0000

Data Index: 369709 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.0749. Min Act: -0.0000

Data Index: 193299 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9424. Min Act: -0.0000

Data Index: 886717 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 1.3434. Min Range: -1.3434

Max Act: 1.1245. Min Act: -0.0000

Data Index: 524138 (The Pile)

Max Activating Token Index: 550

Text #11

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9151. Min Act: -0.0000

Data Index: 10260 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1639771 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1264217 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1227796 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9165. Min Act: -0.0000

Data Index: 232177 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1346480 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1298406 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1086005 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.3434. Min Range: -1.3434

Max Act: 0.7858. Min Act: -0.0000

Data Index: 413339 (The Pile)

Max Activating Token Index: 121