Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 617 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1331329 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.2098. Min Act: -0.0001

Data Index: 63197 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1760. Min Act: -0.0001

Data Index: 108564 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1785. Min Act: -0.0001

Data Index: 16884 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1820. Min Act: -0.0001

Data Index: 659694 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1585. Min Act: -0.0001

Data Index: 584110 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1616. Min Act: -0.0001

Data Index: 107119 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1627. Min Act: -0.0001

Data Index: 738816 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1618. Min Act: -0.0001

Data Index: 645962 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1610. Min Act: -0.0001

Data Index: 842842 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1592. Min Act: -0.0001

Data Index: 659026 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1538. Min Act: -0.0001

Data Index: 909096 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1479. Min Act: -0.0001

Data Index: 304541 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1561. Min Act: -0.0001

Data Index: 590041 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1511. Min Act: -0.0001

Data Index: 785167 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1393. Min Act: -0.0001

Data Index: 355141 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1449. Min Act: -0.0001

Data Index: 297758 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1105763 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1342. Min Act: -0.0001

Data Index: 621889 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.2098. Min Range: -0.2098

Max Act: 0.1351. Min Act: -0.0001

Data Index: 249889 (C4 (Web Text))

Max Activating Token Index: 969