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

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

Neuron 5645 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.8840. Min Act: -0.0000

Data Index: 1048762 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.5834. Min Act: -0.0000

Data Index: 127990 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.6547. Min Act: -0.0001

Data Index: 1003401 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.2223. Min Act: -0.0001

Data Index: 1222781 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.3295. Min Act: -0.0000

Data Index: 1333755 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.1224. Min Act: -0.0000

Data Index: 726198 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.7698. Min Act: -0.0000

Data Index: 1217740 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.9298. Min Act: -0.0001

Data Index: 7036 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.5843. Min Act: -0.0000

Data Index: 71502 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.8066. Min Act: -0.0000

Data Index: 1160427 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.7165. Min Act: -0.0000

Data Index: 966796 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.7540. Min Act: -0.0000

Data Index: 1358814 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.7483. Min Act: -0.0000

Data Index: 1180381 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1053788 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.6890. Min Act: -0.0000

Data Index: 23954 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.6310. Min Act: -0.0000

Data Index: 643300 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.8209. Min Act: -0.0000

Data Index: 486999 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.5899. Min Act: -0.0000

Data Index: 1157688 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.6399. Min Act: -0.0001

Data Index: 1171177 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.5241. Min Act: -0.0001

Data Index: 219602 (C4 (Web Text))

Max Activating Token Index: 309