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

Dataset: The Pile

Neuron 5042 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: 0.9196. Min Range: -0.9196

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1822000 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1378668 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1736439 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7243. Min Act: -0.0000

Data Index: 62569 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1377165 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6762. Min Act: -0.0000

Data Index: 935706 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7378. Min Act: -0.0000

Data Index: 947126 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6785. Min Act: -0.0000

Data Index: 286549 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6469. Min Act: 0.0000

Data Index: 1404663 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6441. Min Act: -0.0000

Data Index: 265841 (The Pile)

Max Activating Token Index: 572

Text #10

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1116387 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6427. Min Act: -0.0000

Data Index: 889931 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1958709 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6136. Min Act: -0.0000

Data Index: 762829 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1614254 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6005. Min Act: -0.0000

Data Index: 269244 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6046. Min Act: -0.0000

Data Index: 224418 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1344772 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.5750. Min Act: -0.0000

Data Index: 158701 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.5861. Min Act: -0.0000

Data Index: 246614 (The Pile)

Max Activating Token Index: 251