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

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

Neuron 1973 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0510. Min Act: -0.0004

Data Index: 40825 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0508. Min Act: -0.0004

Data Index: 628139 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0530. Min Act: -0.0004

Data Index: 1080011 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0467. Min Act: -0.0004

Data Index: 713309 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0485. Min Act: -0.0004

Data Index: 515151 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0466. Min Act: -0.0004

Data Index: 914193 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0485. Min Act: -0.0004

Data Index: 582068 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0473. Min Act: -0.0004

Data Index: 387684 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0488. Min Act: -0.0004

Data Index: 519260 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0409. Min Act: -0.0004

Data Index: 778097 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0458. Min Act: -0.0004

Data Index: 787147 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0437. Min Act: -0.0004

Data Index: 337743 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0451. Min Act: -0.0004

Data Index: 882762 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0451. Min Act: -0.0004

Data Index: 615236 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0420. Min Act: -0.0004

Data Index: 1068369 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0431. Min Act: -0.0004

Data Index: 875627 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0427. Min Act: -0.0004

Data Index: 574728 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0444. Min Act: -0.0004

Data Index: 65811 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0461. Min Act: -0.0004

Data Index: 465140 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0530. Min Range: -0.0530

Max Act: 0.0440. Min Act: -0.0004

Data Index: 400307 (C4 (Web Text))

Max Activating Token Index: 76