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

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

Neuron 501 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: 1.1699. Min Range: -1.1699

Max Act: 1.1699. Min Act: 0.0001

Data Index: 168723 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.8659. Min Act: 0.0000

Data Index: 887510 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.7720. Min Act: 0.0001

Data Index: 1181111 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.7265. Min Act: 0.0001

Data Index: 60919 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.7151. Min Act: 0.0001

Data Index: 530183 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6638. Min Act: 0.0001

Data Index: 730224 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6827. Min Act: 0.0000

Data Index: 1263136 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6479. Min Act: 0.0001

Data Index: 29574 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6412. Min Act: -0.0001

Data Index: 1235795 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6310. Min Act: 0.0001

Data Index: 83171 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6085. Min Act: 0.0001

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6011. Min Act: -0.0001

Data Index: 872816 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6020. Min Act: -0.0001

Data Index: 1178918 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.6223. Min Act: -0.0000

Data Index: 407474 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.5816. Min Act: 0.0000

Data Index: 1142727 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.5931. Min Act: 0.0001

Data Index: 1142459 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.5505. Min Act: -0.0001

Data Index: 181684 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.5785. Min Act: -0.0000

Data Index: 535388 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.5635. Min Act: -0.0001

Data Index: 751379 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 1.1699. Min Range: -1.1699

Max Act: 0.5619. Min Act: 0.0001

Data Index: 395681 (C4 (Web Text))

Max Activating Token Index: 553