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

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

Neuron 391 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.7414. Min Act: -0.0000

Data Index: 1250122 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.7509. Min Act: -0.0000

Data Index: 969832 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.6555. Min Act: -0.0000

Data Index: 30886 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.7672. Min Act: -0.0000

Data Index: 1120651 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.7258. Min Act: -0.0000

Data Index: 10841 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.5619. Min Act: -0.0000

Data Index: 417695 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.4531. Min Act: -0.0000

Data Index: 855321 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.5360. Min Act: -0.0000

Data Index: 228688 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.5489. Min Act: -0.0000

Data Index: 145667 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.3452. Min Act: -0.0000

Data Index: 1060805 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.4694. Min Act: -0.0000

Data Index: 885963 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.3437. Min Act: -0.0000

Data Index: 815729 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.4209. Min Act: -0.0000

Data Index: 999011 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.3964. Min Act: -0.0000

Data Index: 547671 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.3911. Min Act: -0.0000

Data Index: 918879 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.2621. Min Act: -0.0000

Data Index: 891315 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.2594. Min Act: -0.0000

Data Index: 959047 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.2523. Min Act: -0.0000

Data Index: 1172248 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.3561. Min Act: -0.0000

Data Index: 1122651 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 2.7672. Min Range: -2.7672

Max Act: 2.2946. Min Act: -0.0000

Data Index: 1220286 (C4 (Web Text))

Max Activating Token Index: 515