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

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

Neuron 2997 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.6670. Min Act: -0.0000

Data Index: 465866 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.6380. Min Act: -0.0001

Data Index: 923907 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.6152. Min Act: -0.0000

Data Index: 207531 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.6330. Min Act: -0.0001

Data Index: 958419 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5823. Min Act: -0.0000

Data Index: 563929 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5960. Min Act: -0.0001

Data Index: 641495 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5690. Min Act: -0.0001

Data Index: 719093 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5305. Min Act: -0.0001

Data Index: 1074629 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5477. Min Act: -0.0001

Data Index: 510520 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5406. Min Act: -0.0001

Data Index: 1279798 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5513. Min Act: -0.0000

Data Index: 313166 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5300. Min Act: -0.0000

Data Index: 216153 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5155. Min Act: -0.0000

Data Index: 603155 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5517. Min Act: -0.0001

Data Index: 1307816 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1094055 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5269. Min Act: -0.0001

Data Index: 105484 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5453. Min Act: -0.0000

Data Index: 223946 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5227. Min Act: -0.0000

Data Index: 529544 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1127587 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4754. Min Act: -0.0000

Data Index: 5439 (C4 (Web Text))

Max Activating Token Index: 751