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

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

Neuron 5300 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7046. Min Range: -4.7046

Max Act: 4.7046. Min Act: -0.0000

Data Index: 939633 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.8262. Min Act: -0.0000

Data Index: 219604 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.7690. Min Act: -0.0000

Data Index: 231655 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.7908. Min Act: -0.0000

Data Index: 401270 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.6510. Min Act: -0.0000

Data Index: 977210 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.8718. Min Act: -0.0000

Data Index: 1301788 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.5285. Min Act: -0.0000

Data Index: 1002453 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.8018. Min Act: -0.0000

Data Index: 475772 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.3504. Min Act: -0.0000

Data Index: 687537 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.2407. Min Act: -0.0000

Data Index: 941822 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.0150. Min Act: -0.0000

Data Index: 165732 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.1383. Min Act: -0.0000

Data Index: 1295567 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 4.7046. Min Range: -4.7046

Max Act: 2.8054. Min Act: -0.0000

Data Index: 927859 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 4.7046. Min Range: -4.7046

Max Act: 2.8428. Min Act: -0.0000

Data Index: 1247733 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 4.7046. Min Range: -4.7046

Max Act: 3.0202. Min Act: -0.0000

Data Index: 352940 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 4.7046. Min Range: -4.7046

Max Act: 2.8004. Min Act: -0.0000

Data Index: 305991 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 4.7046. Min Range: -4.7046

Max Act: 2.4985. Min Act: -0.0000

Data Index: 340734 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 4.7046. Min Range: -4.7046

Max Act: 2.6759. Min Act: -0.0000

Data Index: 241300 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 4.7046. Min Range: -4.7046

Max Act: 2.4822. Min Act: -0.0000

Data Index: 1356477 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 4.7046. Min Range: -4.7046

Max Act: 2.6213. Min Act: -0.0000

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 622