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

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

Neuron 725 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: 5.7308. Min Range: -5.7308

Max Act: 5.7308. Min Act: -0.0000

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.3589. Min Act: -0.0000

Data Index: 976200 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.4018. Min Act: -0.0000

Data Index: 1204185 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.2244. Min Act: -0.0000

Data Index: 1242016 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 5.7308. Min Range: -5.7308

Max Act: 4.2379. Min Act: -0.0000

Data Index: 937916 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 5.7308. Min Range: -5.7308

Max Act: 4.0370. Min Act: -0.0000

Data Index: 1097762 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.7667. Min Act: -0.0000

Data Index: 354801 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.4982. Min Act: -0.0000

Data Index: 528274 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.4588. Min Act: -0.0000

Data Index: 1517603 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.4122. Min Act: -0.0000

Data Index: 26622 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.3208. Min Act: -0.0000

Data Index: 1154925 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.3014. Min Act: -0.0000

Data Index: 1050948 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.4054. Min Act: -0.0000

Data Index: 180159 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 5.7308. Min Range: -5.7308

Max Act: 2.9525. Min Act: -0.0000

Data Index: 552533 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.0021. Min Act: -0.0000

Data Index: 58079 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.1106. Min Act: -0.0000

Data Index: 477205 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 5.7308. Min Range: -5.7308

Max Act: 2.8769. Min Act: -0.0000

Data Index: 1024678 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 5.7308. Min Range: -5.7308

Max Act: 2.8758. Min Act: -0.0000

Data Index: 1232504 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 5.7308. Min Range: -5.7308

Max Act: 3.0048. Min Act: -0.0000

Data Index: 1551193 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 5.7308. Min Range: -5.7308

Max Act: 2.8048. Min Act: -0.0000

Data Index: 563655 (C4 (Web Text))

Max Activating Token Index: 69