Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3702 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0564. Min Act: -0.0001

Data Index: 753196 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0585. Min Act: -0.0001

Data Index: 743937 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0001

Data Index: 54731 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1135102 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1175657 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0530. Min Act: -0.0001

Data Index: 772647 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0505. Min Act: -0.0001

Data Index: 754847 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0551. Min Act: -0.0001

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1216152 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1024735 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0448. Min Act: -0.0001

Data Index: 802869 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0468. Min Act: -0.0001

Data Index: 907712 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1012994 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0458. Min Act: -0.0001

Data Index: 883598 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0479. Min Act: -0.0001

Data Index: 363103 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1015067 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0478. Min Act: -0.0001

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0448. Min Act: -0.0001

Data Index: 263064 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0462. Min Act: -0.0001

Data Index: 356123 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1258450 (C4 (Web Text))

Max Activating Token Index: 447