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

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

Neuron 5712 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: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0001

Data Index: 924860 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1538. Min Act: -0.0001

Data Index: 555866 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1585. Min Act: -0.0001

Data Index: 735965 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1336797 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1270. Min Act: -0.0001

Data Index: 756112 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1169. Min Act: -0.0001

Data Index: 344593 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1182. Min Act: -0.0001

Data Index: 999512 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1056919 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1013. Min Act: -0.0001

Data Index: 173539 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1028. Min Act: -0.0001

Data Index: 409536 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1021. Min Act: -0.0001

Data Index: 968847 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0983. Min Act: -0.0001

Data Index: 116819 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0685. Min Act: -0.0001

Data Index: 351499 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0669. Min Act: -0.0001

Data Index: 634750 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0644. Min Act: -0.0001

Data Index: 734864 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0652. Min Act: -0.0001

Data Index: 132342 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0632. Min Act: -0.0000

Data Index: 24452 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0570. Min Act: -0.0000

Data Index: 814634 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1000019 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0591. Min Act: -0.0000

Data Index: 399995 (C4 (Web Text))

Max Activating Token Index: 56