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

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

Neuron 708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.9654. Min Act: -0.0000

Data Index: 219206 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.9121. Min Act: -0.0001

Data Index: 679541 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8208. Min Act: -0.0000

Data Index: 975645 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8796. Min Act: -0.0000

Data Index: 606930 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1305051 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.9122. Min Act: -0.0000

Data Index: 779599 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8942. Min Act: -0.0000

Data Index: 141969 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8812. Min Act: -0.0000

Data Index: 399558 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8257. Min Act: -0.0000

Data Index: 402455 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8887. Min Act: -0.0000

Data Index: 988792 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8451. Min Act: -0.0001

Data Index: 869468 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8434. Min Act: -0.0000

Data Index: 920675 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1309646 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1262918 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8412. Min Act: -0.0000

Data Index: 599088 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7451. Min Act: -0.0000

Data Index: 105756 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8917. Min Act: -0.0000

Data Index: 431092 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1177897 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8273. Min Act: -0.0000

Data Index: 142601 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8018. Min Act: -0.0000

Data Index: 854554 (C4 (Web Text))

Max Activating Token Index: 8