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

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

Neuron 5396 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.7919. Min Act: -0.0001

Data Index: 231741 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.7177. Min Act: -0.0001

Data Index: 1137014 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.7061. Min Act: -0.0001

Data Index: 110672 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5888. Min Act: -0.0001

Data Index: 912290 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5494. Min Act: -0.0001

Data Index: 1314557 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5898. Min Act: -0.0001

Data Index: 1205106 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5358. Min Act: -0.0001

Data Index: 965139 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5280. Min Act: -0.0001

Data Index: 1028120 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5155. Min Act: -0.0001

Data Index: 946793 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5888. Min Act: -0.0001

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5204. Min Act: -0.0001

Data Index: 1188444 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5104. Min Act: -0.0001

Data Index: 465910 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5297. Min Act: -0.0001

Data Index: 629617 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5596. Min Act: -0.0001

Data Index: 361354 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5405. Min Act: -0.0001

Data Index: 135892 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5385. Min Act: -0.0001

Data Index: 869038 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5527. Min Act: -0.0001

Data Index: 1606864 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5450. Min Act: -0.0001

Data Index: 846811 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5465. Min Act: -0.0001

Data Index: 658836 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.7919. Min Range: -0.7919

Max Act: 0.5329. Min Act: -0.0001

Data Index: 368204 (C4 (Web Text))

Max Activating Token Index: 795