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

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

Neuron 3642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1788. Min Act: -0.0001

Data Index: 916436 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1748. Min Act: -0.0000

Data Index: 574817 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1689. Min Act: -0.0001

Data Index: 937962 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1616. Min Act: -0.0000

Data Index: 366079 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1596. Min Act: -0.0000

Data Index: 882570 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1745. Min Act: -0.0000

Data Index: 669005 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1589. Min Act: -0.0001

Data Index: 508661 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1517. Min Act: -0.0001

Data Index: 42221 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1543. Min Act: -0.0000

Data Index: 481187 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1526. Min Act: -0.0000

Data Index: 33753 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1518. Min Act: -0.0000

Data Index: 72851 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1414. Min Act: -0.0000

Data Index: 569002 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1428. Min Act: -0.0000

Data Index: 131140 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1355. Min Act: -0.0001

Data Index: 949151 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1449. Min Act: -0.0000

Data Index: 538178 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1057374 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1331. Min Act: -0.0001

Data Index: 508019 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1249. Min Act: -0.0000

Data Index: 280151 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1326. Min Act: -0.0000

Data Index: 187337 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.1788. Min Range: -0.1788

Max Act: 0.1072. Min Act: -0.0000

Data Index: 393911 (C4 (Web Text))

Max Activating Token Index: 841