Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 708 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.8495. Min Act: -0.0001

Data Index: 693679 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7348. Min Act: -0.0001

Data Index: 1266724 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7208. Min Act: -0.0001

Data Index: 1052768 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7322. Min Act: -0.0001

Data Index: 818214 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7293. Min Act: -0.0001

Data Index: 158334 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.7093. Min Act: -0.0001

Data Index: 954705 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6607. Min Act: -0.0001

Data Index: 585785 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6671. Min Act: -0.0001

Data Index: 1050670 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6849. Min Act: -0.0001

Data Index: 829022 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6286. Min Act: -0.0001

Data Index: 1155892 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6026. Min Act: -0.0001

Data Index: 1019681 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6248. Min Act: -0.0001

Data Index: 1054636 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.6060. Min Act: -0.0001

Data Index: 900503 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5942. Min Act: -0.0001

Data Index: 1357151 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5878. Min Act: -0.0001

Data Index: 682875 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5908. Min Act: -0.0001

Data Index: 548815 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5256. Min Act: -0.0001

Data Index: 919621 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5470. Min Act: -0.0001

Data Index: 1320370 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5486. Min Act: -0.0001

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.8495. Min Range: -0.8495

Max Act: 0.5606. Min Act: -0.0001

Data Index: 842163 (C4 (Web Text))

Max Activating Token Index: 242