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

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

Neuron 358 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: 1.1612. Min Range: -1.1612

Max Act: 1.1612. Min Act: -0.0001

Data Index: 1114426 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.9530. Min Act: -0.0000

Data Index: 51020 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.9936. Min Act: -0.0001

Data Index: 265100 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1343210 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.9276. Min Act: -0.0001

Data Index: 899256 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8684. Min Act: -0.0000

Data Index: 323511 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1339643 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.9140. Min Act: -0.0001

Data Index: 573212 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8016. Min Act: -0.0000

Data Index: 568186 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1227922 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8753. Min Act: -0.0001

Data Index: 709319 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7906. Min Act: -0.0000

Data Index: 615146 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.9314. Min Act: -0.0000

Data Index: 967700 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8605. Min Act: -0.0000

Data Index: 69580 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7970. Min Act: -0.0001

Data Index: 597006 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8335. Min Act: -0.0000

Data Index: 236316 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 1.1612. Min Range: -1.1612

Max Act: 1.0539. Min Act: -0.0000

Data Index: 80102 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7906. Min Act: -0.0000

Data Index: 104622 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8292. Min Act: -0.0000

Data Index: 28500 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7536. Min Act: -0.0001

Data Index: 1136543 (C4 (Web Text))

Max Activating Token Index: 31