Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1065 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.9076. Min Act: -0.0001

Data Index: 445737 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8244. Min Act: -0.0001

Data Index: 468995 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1293244 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1270648 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.8594. Min Act: -0.0001

Data Index: 1289651 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7862. Min Act: -0.0001

Data Index: 1122387 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7040. Min Act: -0.0001

Data Index: 1336357 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7754. Min Act: -0.0001

Data Index: 1223154 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7428. Min Act: -0.0001

Data Index: 1197634 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7460. Min Act: -0.0001

Data Index: 733855 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7218. Min Act: -0.0001

Data Index: 574840 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7324. Min Act: -0.0000

Data Index: 838050 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1008888 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7505. Min Act: -0.0001

Data Index: 711186 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6997. Min Act: -0.0001

Data Index: 849495 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7201. Min Act: -0.0001

Data Index: 132228 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7317. Min Act: -0.0001

Data Index: 385129 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7414. Min Act: -0.0001

Data Index: 660177 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.7152. Min Act: -0.0001

Data Index: 469193 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.9076. Min Range: -0.9076

Max Act: 0.6139. Min Act: -0.0001

Data Index: 1130928 (C4 (Web Text))

Max Activating Token Index: 627