Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.6427. Min Act: -0.0001

Data Index: 1321918 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3801. Min Act: -0.0001

Data Index: 453279 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.4659. Min Act: -0.0001

Data Index: 1319931 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3512. Min Act: -0.0001

Data Index: 1253531 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.4138. Min Act: -0.0001

Data Index: 920555 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3112. Min Act: -0.0001

Data Index: 978669 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.2469. Min Act: -0.0001

Data Index: 504569 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3096. Min Act: -0.0001

Data Index: 388660 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.3064. Min Act: -0.0000

Data Index: 42608 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.2254. Min Act: -0.0001

Data Index: 242189 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1878. Min Act: -0.0001

Data Index: 548738 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1910. Min Act: -0.0001

Data Index: 1256149 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.2356. Min Act: -0.0001

Data Index: 1017751 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1667. Min Act: -0.0001

Data Index: 432962 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.0835. Min Act: -0.0001

Data Index: 143363 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1509. Min Act: -0.0001

Data Index: 331414 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1137. Min Act: -0.0001

Data Index: 1280645 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1692. Min Act: -0.0001

Data Index: 599183 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.6427. Min Range: -1.6427

Max Act: 0.9649. Min Act: -0.0001

Data Index: 2828 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 1.6427. Min Range: -1.6427

Max Act: 1.1960. Min Act: -0.0001

Data Index: 852759 (C4 (Web Text))

Max Activating Token Index: 537