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

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

Neuron 2638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.6082. Min Act: -0.0000

Data Index: 616947 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1142070 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.5592. Min Act: -0.0000

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.3854. Min Act: -0.0000

Data Index: 1240492 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.4203. Min Act: -0.0000

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.3283. Min Act: -0.0000

Data Index: 671617 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.2910. Min Act: -0.0000

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.2709. Min Act: -0.0000

Data Index: 226727 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1139732 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.1014. Min Act: -0.0000

Data Index: 261503 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.1506. Min Act: -0.0000

Data Index: 485213 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.0134. Min Act: -0.0000

Data Index: 141282 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.0766. Min Act: -0.0000

Data Index: 896554 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 1.6082. Min Range: -1.6082

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1323485 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.6082. Min Range: -1.6082

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1021544 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 1.6082. Min Range: -1.6082

Max Act: 0.8563. Min Act: -0.0000

Data Index: 801013 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1227548 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.6082. Min Range: -1.6082

Max Act: 1.0249. Min Act: -0.0000

Data Index: 707142 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.6082. Min Range: -1.6082

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1294888 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.6082. Min Range: -1.6082

Max Act: 0.9744. Min Act: -0.0000

Data Index: 1436617 (Python Code)

Max Activating Token Index: 448