Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4809 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2757. Min Range: -1.2757

Max Act: 1.2757. Min Act: -0.0000

Data Index: 93163 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.2757. Min Range: -1.2757

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1021504 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1488146 (Python Code)

Max Activating Token Index: 630

Text #3

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1300249 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8147. Min Act: -0.0000

Data Index: 654679 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7827. Min Act: -0.0000

Data Index: 180958 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1030417 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7657. Min Act: -0.0000

Data Index: 616511 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7356. Min Act: -0.0000

Data Index: 916937 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6954. Min Act: -0.0000

Data Index: 186470 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6785. Min Act: -0.0000

Data Index: 643317 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7111. Min Act: -0.0000

Data Index: 581643 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6911. Min Act: -0.0000

Data Index: 813895 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.7111. Min Act: -0.0000

Data Index: 875521 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1107146 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1176677 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6450. Min Act: -0.0000

Data Index: 61777 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6498. Min Act: -0.0000

Data Index: 708661 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6473. Min Act: -0.0000

Data Index: 979695 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.6286. Min Act: -0.0000

Data Index: 347857 (C4 (Web Text))

Max Activating Token Index: 890