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

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

Neuron 4493 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.5819. Min Act: -0.0000

Data Index: 426653 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.5395. Min Act: -0.0000

Data Index: 884381 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.5378. Min Act: -0.0000

Data Index: 207384 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.5312. Min Act: -0.0000

Data Index: 109924 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1221832 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.4032. Min Act: -0.0000

Data Index: 720589 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3959. Min Act: -0.0000

Data Index: 251661 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.4032. Min Act: -0.0000

Data Index: 429877 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.4003. Min Act: -0.0000

Data Index: 898541 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3846. Min Act: -0.0000

Data Index: 179304 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3713. Min Act: -0.0000

Data Index: 861645 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3678. Min Act: -0.0000

Data Index: 322360 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3672. Min Act: -0.0000

Data Index: 200953 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3603. Min Act: -0.0000

Data Index: 45072 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1316742 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3482. Min Act: -0.0000

Data Index: 275357 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1138600 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3355. Min Act: -0.0000

Data Index: 175300 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3451. Min Act: -0.0000

Data Index: 64504 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.5819. Min Range: -0.5819

Max Act: 0.3438. Min Act: -0.0000

Data Index: 557390 (C4 (Web Text))

Max Activating Token Index: 569