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

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

Neuron 2619 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.3708. Min Act: -0.0000

Data Index: 347368 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.4840. Min Act: -0.0000

Data Index: 143843 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.4524. Min Act: -0.0000

Data Index: 135957 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.5577. Min Act: -0.0000

Data Index: 990333 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.5257. Min Act: -0.0000

Data Index: 710419 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.2678. Min Act: -0.0000

Data Index: 287288 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.1982. Min Act: -0.0001

Data Index: 187527 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.4049. Min Act: -0.0001

Data Index: 181799 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.1683. Min Act: -0.0000

Data Index: 796692 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.2306. Min Act: -0.0000

Data Index: 1095923 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.2155. Min Act: -0.0000

Data Index: 985361 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.2195. Min Act: -0.0000

Data Index: 438921 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.0772. Min Act: -0.0001

Data Index: 231387 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.3171. Min Act: -0.0000

Data Index: 1229018 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.0249. Min Act: -0.0000

Data Index: 604825 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 2.5577. Min Range: -2.5577

Max Act: 1.9865. Min Act: -0.0000

Data Index: 57283 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.1042. Min Act: -0.0001

Data Index: 1318661 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.0989. Min Act: -0.0000

Data Index: 716061 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.2048. Min Act: -0.0001

Data Index: 480448 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 2.5577. Min Range: -2.5577

Max Act: 2.0848. Min Act: -0.0000

Data Index: 1201802 (C4 (Web Text))

Max Activating Token Index: 507