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

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

Neuron 2658 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: 5.3054. Min Range: -5.3054

Max Act: 5.3054. Min Act: -0.0000

Data Index: 1254503 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1387. Min Act: -0.0000

Data Index: 834676 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1190. Min Act: -0.0000

Data Index: 110616 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1370. Min Act: -0.0000

Data Index: 887898 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.8833. Min Act: -0.0000

Data Index: 267687 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.3879. Min Act: -0.0000

Data Index: 978889 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.1569. Min Act: -0.0000

Data Index: 542819 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.4783. Min Act: -0.0000

Data Index: 770366 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.0748. Min Act: -0.0000

Data Index: 863293 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.2468. Min Act: -0.0000

Data Index: 1159264 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.0390. Min Act: -0.0000

Data Index: 1156011 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 5.3054. Min Range: -5.3054

Max Act: 3.5519. Min Act: -0.0000

Data Index: 688572 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.1633. Min Act: -0.0000

Data Index: 1179014 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.0292. Min Act: -0.0000

Data Index: 949860 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 5.3054. Min Range: -5.3054

Max Act: 4.1656. Min Act: -0.0000

Data Index: 1143645 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 5.3054. Min Range: -5.3054

Max Act: 3.7482. Min Act: -0.0000

Data Index: 965738 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 5.3054. Min Range: -5.3054

Max Act: 3.8725. Min Act: -0.0000

Data Index: 165452 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 5.3054. Min Range: -5.3054

Max Act: 3.6792. Min Act: -0.0000

Data Index: 851142 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 5.3054. Min Range: -5.3054

Max Act: 3.6822. Min Act: -0.0000

Data Index: 1127426 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 5.3054. Min Range: -5.3054

Max Act: 3.7881. Min Act: -0.0000

Data Index: 810781 (C4 (Web Text))

Max Activating Token Index: 1009