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

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

Neuron 1499 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1663. Min Range: -1.1663

Max Act: 1.1421. Min Act: -0.0000

Data Index: 10807 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 1.1663. Min Range: -1.1663

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1261898 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.1663. Min Range: -1.1663

Max Act: 1.1570. Min Act: -0.0001

Data Index: 1161615 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.1663. Min Range: -1.1663

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1089748 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.1663. Min Range: -1.1663

Max Act: 1.0819. Min Act: -0.0001

Data Index: 459085 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.1663. Min Range: -1.1663

Max Act: 1.0405. Min Act: -0.0001

Data Index: 561169 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9591. Min Act: -0.0001

Data Index: 568054 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1116170 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9812. Min Act: -0.0001

Data Index: 768588 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9770. Min Act: -0.0001

Data Index: 121699 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9955. Min Act: -0.0001

Data Index: 1229097 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9726. Min Act: -0.0001

Data Index: 1132055 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9202. Min Act: -0.0001

Data Index: 350642 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9092. Min Act: -0.0001

Data Index: 1261992 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.9160. Min Act: -0.0001

Data Index: 1011456 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.8835. Min Act: -0.0001

Data Index: 622533 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.8828. Min Act: -0.0001

Data Index: 276675 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.8685. Min Act: -0.0001

Data Index: 852462 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.8988. Min Act: -0.0001

Data Index: 435620 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 1.1663. Min Range: -1.1663

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1140477 (C4 (Web Text))

Max Activating Token Index: 992