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

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

Neuron 2825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.1826. Min Act: -0.0001

Data Index: 867050 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1125965 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.1826. Min Range: -1.1826

Max Act: 1.0248. Min Act: -0.0001

Data Index: 874012 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8817. Min Act: -0.0001

Data Index: 1318288 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9284. Min Act: -0.0001

Data Index: 1229249 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9044. Min Act: -0.0001

Data Index: 705332 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9635. Min Act: -0.0001

Data Index: 1302653 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8694. Min Act: -0.0001

Data Index: 464476 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9404. Min Act: -0.0000

Data Index: 46351 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9018. Min Act: -0.0001

Data Index: 1217242 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8060. Min Act: -0.0001

Data Index: 1191001 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8806. Min Act: -0.0001

Data Index: 447358 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9402. Min Act: -0.0000

Data Index: 757569 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9047. Min Act: -0.0001

Data Index: 1225355 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8157. Min Act: -0.0001

Data Index: 1001754 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.9336. Min Act: -0.0001

Data Index: 1144141 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.7723. Min Act: -0.0001

Data Index: 1203953 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.7436. Min Act: -0.0001

Data Index: 525706 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.7189. Min Act: -0.0001

Data Index: 496530 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 1.1826. Min Range: -1.1826

Max Act: 0.8329. Min Act: -0.0001

Data Index: 1181016 (C4 (Web Text))

Max Activating Token Index: 666