Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3122 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.1059. Min Act: -0.0001

Data Index: 19646 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1187932 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0682. Min Act: -0.0001

Data Index: 204808 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0708. Min Act: -0.0001

Data Index: 179539 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0683. Min Act: -0.0001

Data Index: 719859 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0671. Min Act: -0.0001

Data Index: 205932 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1291068 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0646. Min Act: -0.0001

Data Index: 988358 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1352387 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0604. Min Act: -0.0001

Data Index: 750641 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0616. Min Act: -0.0001

Data Index: 754478 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0592. Min Act: -0.0001

Data Index: 491626 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1077455 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1226844 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0606. Min Act: -0.0001

Data Index: 822677 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0582. Min Act: -0.0001

Data Index: 741492 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0552. Min Act: -0.0001

Data Index: 691607 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1200039 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0574. Min Act: -0.0001

Data Index: 515461 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0564. Min Act: -0.0001

Data Index: 293678 (C4 (Web Text))

Max Activating Token Index: 987