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

Dataset: The Pile

Neuron 2737 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7778. Min Act: 0.0000

Data Index: 329962 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7932. Min Act: -0.0000

Data Index: 959613 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1505035 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1120996 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6330. Min Act: 0.0000

Data Index: 1817912 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1560293 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1176855 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1444216 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6653. Min Act: -0.0000

Data Index: 294465 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5143. Min Act: 0.0000

Data Index: 1422556 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5814. Min Act: -0.0000

Data Index: 642531 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1317184 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5037. Min Act: -0.0000

Data Index: 826244 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.4975. Min Act: -0.0000

Data Index: 468992 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5116. Min Act: -0.0000

Data Index: 187351 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.4647. Min Act: -0.0000

Data Index: 103355 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.4853. Min Act: -0.0000

Data Index: 283529 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1079691 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1543189 (The Pile)

Max Activating Token Index: 602

Text #19

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1189094 (The Pile)

Max Activating Token Index: 568