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

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

Neuron 1017 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: 0.2141. Min Range: -0.2141

Max Act: 0.2141. Min Act: -0.0001

Data Index: 779011 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.2029. Min Act: -0.0000

Data Index: 386464 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1979. Min Act: -0.0001

Data Index: 268866 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1733. Min Act: -0.0001

Data Index: 678022 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1318278 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1569. Min Act: -0.0001

Data Index: 158441 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1358020 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1670. Min Act: -0.0001

Data Index: 805819 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1522. Min Act: -0.0001

Data Index: 494503 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1656. Min Act: -0.0001

Data Index: 616973 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1563. Min Act: -0.0001

Data Index: 742603 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1617. Min Act: -0.0001

Data Index: 9526 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1004958 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1189674 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1517. Min Act: -0.0000

Data Index: 333739 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1420. Min Act: -0.0000

Data Index: 924698 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1407540 (Python Code)

Max Activating Token Index: 957

Text #17

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1616447 (Python Code)

Max Activating Token Index: 724

Text #18

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1481635 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 0.2141. Min Range: -0.2141

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1207695 (C4 (Web Text))

Max Activating Token Index: 627