Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1905 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3374. Min Range: -5.3374

Max Act: 5.3374. Min Act: -0.0000

Data Index: 3381 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 5.3374. Min Range: -5.3374

Max Act: 4.3018. Min Act: -0.0000

Data Index: 795310 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.7937. Min Act: -0.0000

Data Index: 1031734 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.7413. Min Act: -0.0000

Data Index: 40626 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.4856. Min Act: -0.0000

Data Index: 202531 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.1863. Min Act: -0.0000

Data Index: 577694 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.3488. Min Act: -0.0000

Data Index: 463982 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.2551. Min Act: -0.0000

Data Index: 780629 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.3797. Min Act: -0.0000

Data Index: 331516 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.2390. Min Act: -0.0000

Data Index: 972385 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 5.3374. Min Range: -5.3374

Max Act: 2.9666. Min Act: -0.0000

Data Index: 758961 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.0207. Min Act: -0.0000

Data Index: 733597 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 5.3374. Min Range: -5.3374

Max Act: 3.1396. Min Act: -0.0000

Data Index: 1160299 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 5.3374. Min Range: -5.3374

Max Act: 2.6978. Min Act: -0.0000

Data Index: 629517 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 5.3374. Min Range: -5.3374

Max Act: 2.9011. Min Act: -0.0000

Data Index: 76086 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 5.3374. Min Range: -5.3374

Max Act: 2.8637. Min Act: -0.0001

Data Index: 917911 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 5.3374. Min Range: -5.3374

Max Act: 2.8248. Min Act: -0.0000

Data Index: 1095403 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 5.3374. Min Range: -5.3374

Max Act: 2.9465. Min Act: -0.0000

Data Index: 1099308 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 5.3374. Min Range: -5.3374

Max Act: 2.9101. Min Act: -0.0000

Data Index: 102200 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 5.3374. Min Range: -5.3374

Max Act: 2.6683. Min Act: -0.0000

Data Index: 911451 (C4 (Web Text))

Max Activating Token Index: 937