Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3739 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1867287 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3372. Min Act: -0.0000

Data Index: 619330 (The Pile)

Max Activating Token Index: 950

Text #2

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1558099 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1798777 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1172836 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3218. Min Act: -0.0000

Data Index: 772636 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1405035 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3294. Min Act: -0.0000

Data Index: 772674 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1911579 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1688459 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3133. Min Act: -0.0000

Data Index: 699468 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1676264 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1949306 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1894815 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1066440 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.3014. Min Act: -0.0000

Data Index: 259259 (The Pile)

Max Activating Token Index: 553

Text #16

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2980. Min Act: -0.0000

Data Index: 831762 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1777828 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1383346 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 0.3486. Min Range: -0.3486

Max Act: 0.2940. Min Act: -0.0000

Data Index: 663 (The Pile)

Max Activating Token Index: 285