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

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

Neuron 3540 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: 1.2705. Min Range: -1.2705

Max Act: 1.2705. Min Act: -0.0000

Data Index: 391633 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.1012. Min Act: -0.0000

Data Index: 731206 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0370. Min Act: -0.0000

Data Index: 785631 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1296332 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1067071 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1092595 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1162956 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9377. Min Act: -0.0000

Data Index: 126283 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9876. Min Act: -0.0000

Data Index: 753924 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1066388 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1219863 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.7667. Min Act: -0.0000

Data Index: 791473 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.7673. Min Act: -0.0000

Data Index: 972125 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.7697. Min Act: -0.0000

Data Index: 467092 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.7162. Min Act: -0.0000

Data Index: 737083 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1308798 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.6718. Min Act: -0.0001

Data Index: 1015615 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.6509. Min Act: -0.0000

Data Index: 504479 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.6695. Min Act: -0.0000

Data Index: 812524 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.6500. Min Act: -0.0000

Data Index: 165702 (C4 (Web Text))

Max Activating Token Index: 294