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

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

Neuron 3397 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6887. Min Range: -3.6887

Max Act: 3.6887. Min Act: -0.0000

Data Index: 320222 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.8429. Min Act: -0.0000

Data Index: 971249 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 3.6887. Min Range: -3.6887

Max Act: 3.1123. Min Act: -0.0000

Data Index: 634170 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.5900. Min Act: -0.0000

Data Index: 464551 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.6405. Min Act: -0.0000

Data Index: 106448 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 3.6887. Min Range: -3.6887

Max Act: 3.0563. Min Act: -0.0000

Data Index: 106543 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.4335. Min Act: -0.0000

Data Index: 337452 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.6562. Min Act: -0.0000

Data Index: 336450 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.4416. Min Act: -0.0000

Data Index: 1249705 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.7087. Min Act: -0.0000

Data Index: 847685 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.6579. Min Act: -0.0000

Data Index: 554353 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.6481. Min Act: -0.0000

Data Index: 791162 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.6300. Min Act: -0.0000

Data Index: 715734 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.3839. Min Act: -0.0000

Data Index: 794445 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.5927. Min Act: -0.0000

Data Index: 292765 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.2359. Min Act: -0.0000

Data Index: 849252 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.4697. Min Act: -0.0000

Data Index: 975366 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.4292. Min Act: -0.0000

Data Index: 1076012 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.6853. Min Act: -0.0000

Data Index: 1178247 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.6887. Min Range: -3.6887

Max Act: 2.5660. Min Act: -0.0000

Data Index: 1246371 (C4 (Web Text))

Max Activating Token Index: 637