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

Dataset: The Pile

Neuron 1530 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8819. Min Range: -5.8819

Max Act: 5.8819. Min Act: -0.0000

Data Index: 1268381 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 5.8819. Min Range: -5.8819

Max Act: 5.7262. Min Act: -0.0000

Data Index: 1148541 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 5.8819. Min Range: -5.8819

Max Act: 5.5850. Min Act: -0.0000

Data Index: 1254827 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 5.8819. Min Range: -5.8819

Max Act: 5.1300. Min Act: -0.0000

Data Index: 220040 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 5.8819. Min Range: -5.8819

Max Act: 5.0215. Min Act: -0.0000

Data Index: 1155690 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.8169. Min Act: -0.0000

Data Index: 395273 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.6100. Min Act: -0.0000

Data Index: 937502 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.4116. Min Act: -0.0000

Data Index: 1869033 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.8579. Min Act: -0.0000

Data Index: 486285 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 5.8819. Min Range: -5.8819

Max Act: 5.1727. Min Act: -0.0000

Data Index: 1776090 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 5.8819. Min Range: -5.8819

Max Act: 5.0235. Min Act: -0.0000

Data Index: 1454694 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.9541. Min Act: -0.0000

Data Index: 1022534 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.6328. Min Act: -0.0000

Data Index: 805092 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.5494. Min Act: -0.0000

Data Index: 991375 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.6905. Min Act: -0.0000

Data Index: 1533645 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.4993. Min Act: -0.0000

Data Index: 100638 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.4739. Min Act: -0.0000

Data Index: 580602 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.6071. Min Act: -0.0000

Data Index: 1260971 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.7625. Min Act: -0.0000

Data Index: 260546 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 5.8819. Min Range: -5.8819

Max Act: 4.5852. Min Act: -0.0000

Data Index: 557401 (The Pile)

Max Activating Token Index: 162