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

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

Neuron 4814 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5728. Min Range: -4.5728

Max Act: 4.5728. Min Act: -0.0000

Data Index: 664862 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.9219. Min Act: -0.0000

Data Index: 1171202 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.4849. Min Act: -0.0000

Data Index: 470348 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.6436. Min Act: -0.0000

Data Index: 1280260 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.6320. Min Act: -0.0000

Data Index: 179782 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.5706. Min Act: -0.0000

Data Index: 422105 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.5091. Min Act: -0.0000

Data Index: 611068 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.4655. Min Act: -0.0000

Data Index: 288160 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.4660. Min Act: -0.0000

Data Index: 625062 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.6071. Min Act: -0.0000

Data Index: 660475 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.0764. Min Act: -0.0000

Data Index: 773584 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.3839. Min Act: -0.0000

Data Index: 1209386 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.1873. Min Act: -0.0000

Data Index: 709023 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.2701. Min Act: -0.0000

Data Index: 514078 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.2608. Min Act: -0.0000

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.2473. Min Act: -0.0000

Data Index: 571314 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.2118. Min Act: -0.0000

Data Index: 1310745 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 4.5728. Min Range: -4.5728

Max Act: 3.3011. Min Act: -0.0000

Data Index: 456313 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 4.5728. Min Range: -4.5728

Max Act: 2.9765. Min Act: -0.0000

Data Index: 987059 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 4.5728. Min Range: -4.5728

Max Act: 2.9607. Min Act: -0.0000

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 310