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

Dataset: The Pile

Neuron 2775 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: 3.1926. Min Range: -3.1926

Max Act: 3.1926. Min Act: -0.0000

Data Index: 1418265 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 3.1926. Min Range: -3.1926

Max Act: 2.1915. Min Act: -0.0000

Data Index: 83802 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1711906 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.7853. Min Act: -0.0000

Data Index: 589810 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.4394. Min Act: -0.0000

Data Index: 1342929 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.5449. Min Act: -0.0000

Data Index: 1710275 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.3149. Min Act: -0.0000

Data Index: 285418 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.1591. Min Act: -0.0000

Data Index: 599378 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.3164. Min Act: -0.0000

Data Index: 1124350 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.2169. Min Act: -0.0000

Data Index: 545796 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.0819. Min Act: -0.0000

Data Index: 1247779 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.1195. Min Act: -0.0000

Data Index: 218336 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1189306 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1695237 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.1218. Min Act: -0.0000

Data Index: 652690 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1380740 (The Pile)

Max Activating Token Index: 66

Text #16

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1634200 (The Pile)

Max Activating Token Index: 684

Text #17

Max Range: 3.1926. Min Range: -3.1926

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1712166 (The Pile)

Max Activating Token Index: 28

Text #18

Max Range: 3.1926. Min Range: -3.1926

Max Act: 0.9755. Min Act: -0.0000

Data Index: 308978 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 3.1926. Min Range: -3.1926

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1746937 (The Pile)

Max Activating Token Index: 628