Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.6645. Min Act: -0.0001

Data Index: 720731 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.6735. Min Act: -0.0001

Data Index: 137547 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.5613. Min Act: -0.0001

Data Index: 167266 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.4678. Min Act: -0.0001

Data Index: 832830 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.2680. Min Act: -0.0001

Data Index: 577399 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.2526. Min Act: -0.0001

Data Index: 162509 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.1644. Min Act: -0.0001

Data Index: 1255304 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.0580. Min Act: -0.0001

Data Index: 960159 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.0802. Min Act: -0.0001

Data Index: 271976 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.1187. Min Act: -0.0001

Data Index: 889141 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.1752. Min Act: -0.0001

Data Index: 1038677 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.0807. Min Act: -0.0001

Data Index: 1096717 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.0639. Min Act: -0.0001

Data Index: 740393 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.0617. Min Act: -0.0001

Data Index: 226265 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.0263. Min Act: -0.0001

Data Index: 769010 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.0141. Min Act: -0.0001

Data Index: 1064892 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 1.6735. Min Range: -1.6735

Max Act: 1.0177. Min Act: -0.0001

Data Index: 898353 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 1.6735. Min Range: -1.6735

Max Act: 0.8859. Min Act: -0.0001

Data Index: 915495 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.6735. Min Range: -1.6735

Max Act: 0.9651. Min Act: -0.0001

Data Index: 199196 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.6735. Min Range: -1.6735

Max Act: 0.9988. Min Act: -0.0001

Data Index: 551073 (C4 (Web Text))

Max Activating Token Index: 700