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

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

Neuron 5750 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5951. Min Act: -0.0000

Data Index: 671647 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6031. Min Act: -0.0000

Data Index: 119879 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1091833 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5259. Min Act: -0.0000

Data Index: 149251 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5469. Min Act: -0.0000

Data Index: 946995 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1028949 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4995. Min Act: -0.0000

Data Index: 466893 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1008150 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4551. Min Act: -0.0000

Data Index: 39036 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4755. Min Act: -0.0000

Data Index: 522332 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4579. Min Act: -0.0000

Data Index: 740944 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1256982 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1278738 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4732. Min Act: -0.0000

Data Index: 894923 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4425. Min Act: -0.0000

Data Index: 697851 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4616. Min Act: -0.0000

Data Index: 884433 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4207. Min Act: -0.0000

Data Index: 209874 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1353280 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4443. Min Act: -0.0000

Data Index: 464574 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4389. Min Act: -0.0000

Data Index: 935700 (C4 (Web Text))

Max Activating Token Index: 618