Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5120 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5112. Min Act: -0.0002

Data Index: 428731 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5176. Min Act: -0.0002

Data Index: 527093 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5173. Min Act: -0.0002

Data Index: 276671 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4985. Min Act: -0.0002

Data Index: 289856 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5048. Min Act: -0.0002

Data Index: 926938 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5011. Min Act: -0.0002

Data Index: 669141 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5019. Min Act: -0.0002

Data Index: 1224000 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4995. Min Act: -0.0002

Data Index: 1151520 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4886. Min Act: -0.0002

Data Index: 59685 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4991. Min Act: -0.0002

Data Index: 1147742 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5018. Min Act: -0.0002

Data Index: 487338 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4839. Min Act: -0.0002

Data Index: 136765 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4839. Min Act: -0.0002

Data Index: 552865 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4798. Min Act: -0.0002

Data Index: 1064565 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4840. Min Act: -0.0002

Data Index: 240927 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4902. Min Act: -0.0002

Data Index: 1285838 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4808. Min Act: -0.0002

Data Index: 1344891 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4741. Min Act: -0.0002

Data Index: 903858 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4811. Min Act: -0.0002

Data Index: 1243007 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4854. Min Act: -0.0002

Data Index: 409476 (C4 (Web Text))

Max Activating Token Index: 313