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

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

Neuron 1063 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: 1.0106. Min Range: -1.0106

Max Act: 1.0106. Min Act: -0.0001

Data Index: 1621983 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1329392 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1033070 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.9562. Min Act: -0.0000

Data Index: 923902 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1319539 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8734. Min Act: -0.0001

Data Index: 588292 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.9196. Min Act: -0.0000

Data Index: 627349 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8510. Min Act: -0.0000

Data Index: 520561 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1432135 (Python Code)

Max Activating Token Index: 905

Text #9

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8281. Min Act: -0.0000

Data Index: 317637 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1315691 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1591130 (Python Code)

Max Activating Token Index: 507

Text #12

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1068957 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8083. Min Act: -0.0000

Data Index: 179570 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8567. Min Act: -0.0000

Data Index: 537253 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1158129 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8020. Min Act: -0.0000

Data Index: 824552 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.7968. Min Act: -0.0000

Data Index: 979706 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.7710. Min Act: -0.0000

Data Index: 74517 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.0106. Min Range: -1.0106

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1138200 (C4 (Web Text))

Max Activating Token Index: 253