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

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

Neuron 4004 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2475. Min Act: -0.0000

Data Index: 710816 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2001. Min Act: -0.0001

Data Index: 869339 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2043. Min Act: -0.0000

Data Index: 250663 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1278022 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1219312 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1706. Min Act: -0.0000

Data Index: 329782 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1927. Min Act: -0.0000

Data Index: 467336 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1904. Min Act: -0.0001

Data Index: 412780 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1272293 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1345290 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1693. Min Act: -0.0000

Data Index: 302262 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1230751 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1684. Min Act: -0.0001

Data Index: 403602 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1523. Min Act: -0.0000

Data Index: 221412 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1646. Min Act: -0.0000

Data Index: 757110 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1747. Min Act: -0.0000

Data Index: 913211 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1110449 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.2106. Min Act: -0.0000

Data Index: 440692 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1594. Min Act: -0.0000

Data Index: 263510 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.2475. Min Range: -0.2475

Max Act: 0.1546. Min Act: -0.0001

Data Index: 434761 (C4 (Web Text))

Max Activating Token Index: 981