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

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

Neuron 5860 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2474. Min Range: -2.2474

Max Act: 2.2474. Min Act: -0.0000

Data Index: 845030 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 2.2474. Min Range: -2.2474

Max Act: 2.0438. Min Act: -0.0000

Data Index: 1150553 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.9278. Min Act: -0.0000

Data Index: 1117613 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.8984. Min Act: -0.0000

Data Index: 121808 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.7557. Min Act: -0.0000

Data Index: 773996 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.5913. Min Act: -0.0000

Data Index: 408898 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.6724. Min Act: -0.0000

Data Index: 822350 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.6528. Min Act: -0.0000

Data Index: 566119 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.7254. Min Act: -0.0000

Data Index: 98476 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.6054. Min Act: -0.0000

Data Index: 1266215 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1107000 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1077852 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.5582. Min Act: -0.0000

Data Index: 1313425 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.4597. Min Act: -0.0000

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.4408. Min Act: -0.0000

Data Index: 699610 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.4313. Min Act: -0.0000

Data Index: 838495 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.4025. Min Act: -0.0000

Data Index: 1336718 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.3274. Min Act: -0.0000

Data Index: 714682 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.3896. Min Act: -0.0000

Data Index: 586142 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1133114 (C4 (Web Text))

Max Activating Token Index: 448