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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 935 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.3593. Min Act: -0.0002

Data Index: 674067 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.3134. Min Act: -0.0002

Data Index: 232198 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1986. Min Act: -0.0002

Data Index: 506875 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1606. Min Act: -0.0001

Data Index: 197440 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.0835. Min Act: -0.0001

Data Index: 919123 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.3246. Min Act: -0.0002

Data Index: 637477 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2401. Min Act: -0.0001

Data Index: 235344 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2261. Min Act: -0.0002

Data Index: 1334803 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2662. Min Act: -0.0002

Data Index: 1243488 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1758. Min Act: -0.0002

Data Index: 1240191 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.3103. Min Act: -0.0001

Data Index: 51629 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1149. Min Act: -0.0002

Data Index: 186732 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1329. Min Act: -0.0001

Data Index: 41958 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1574. Min Act: -0.0002

Data Index: 967960 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.0891. Min Act: -0.0002

Data Index: 1176429 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.0905. Min Act: -0.0002

Data Index: 222618 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1869. Min Act: -0.0001

Data Index: 103401 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.9889. Min Act: -0.0001

Data Index: 349571 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1185. Min Act: -0.0002

Data Index: 277957 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2063. Min Act: -0.0002

Data Index: 1289485 (C4 (Web Text))

Max Activating Token Index: 141