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

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

Neuron 1242 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5756. Min Act: -0.0000

Data Index: 7922 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5747. Min Act: -0.0000

Data Index: 234356 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4764. Min Act: -0.0000

Data Index: 702455 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1049218 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4259. Min Act: -0.0000

Data Index: 532948 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4298. Min Act: -0.0000

Data Index: 980579 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4115. Min Act: -0.0000

Data Index: 110149 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3850. Min Act: -0.0000

Data Index: 178088 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3902. Min Act: -0.0000

Data Index: 68607 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3573. Min Act: -0.0000

Data Index: 134114 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3923. Min Act: -0.0000

Data Index: 585526 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3894. Min Act: -0.0000

Data Index: 925304 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3729. Min Act: -0.0000

Data Index: 676407 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3564. Min Act: -0.0000

Data Index: 822389 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3630. Min Act: -0.0000

Data Index: 195617 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3573. Min Act: -0.0000

Data Index: 685227 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3563. Min Act: -0.0000

Data Index: 273150 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1223307 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3184. Min Act: -0.0000

Data Index: 848971 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3124. Min Act: -0.0000

Data Index: 532119 (C4 (Web Text))

Max Activating Token Index: 793