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

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

Neuron 2982 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: 0.9570. Min Range: -0.9570

Max Act: 0.9570. Min Act: -0.0000

Data Index: 190462 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1385022 (Python Code)

Max Activating Token Index: 621

Text #2

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1390434 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7128. Min Act: -0.0000

Data Index: 449827 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1150241 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1605840 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1552400 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1276448 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6723. Min Act: -0.0000

Data Index: 81431 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1189463 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6321. Min Act: -0.0000

Data Index: 912428 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1355936 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1403400 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.5858. Min Act: -0.0000

Data Index: 585793 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6289. Min Act: -0.0000

Data Index: 759829 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1555616 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1462687 (Python Code)

Max Activating Token Index: 623

Text #17

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.5587. Min Act: -0.0001

Data Index: 1546833 (Python Code)

Max Activating Token Index: 340

Text #18

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6115. Min Act: -0.0000

Data Index: 407066 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1224754 (C4 (Web Text))

Max Activating Token Index: 69