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

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

Neuron 1020 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: 1.7755. Min Range: -1.7755

Max Act: 1.7755. Min Act: -0.0001

Data Index: 503359 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.4602. Min Act: -0.0001

Data Index: 179172 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.5978. Min Act: -0.0001

Data Index: 557344 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.4556. Min Act: -0.0001

Data Index: 535542 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.4460. Min Act: -0.0001

Data Index: 984566 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.3811. Min Act: -0.0001

Data Index: 133621 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.2583. Min Act: -0.0001

Data Index: 1167259 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1036243 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.1320. Min Act: -0.0001

Data Index: 564657 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.2129. Min Act: -0.0000

Data Index: 655003 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.2155. Min Act: -0.0001

Data Index: 214079 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.1194. Min Act: -0.0001

Data Index: 454927 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.1911. Min Act: -0.0000

Data Index: 69436 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.1478. Min Act: -0.0000

Data Index: 45151 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.2600. Min Act: -0.0000

Data Index: 732297 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.1483. Min Act: -0.0000

Data Index: 829022 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.0997. Min Act: -0.0001

Data Index: 1239513 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.1775. Min Act: -0.0001

Data Index: 191104 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.0339. Min Act: -0.0001

Data Index: 916148 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.7755. Min Range: -1.7755

Max Act: 1.0858. Min Act: -0.0001

Data Index: 1046805 (C4 (Web Text))

Max Activating Token Index: 656