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

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

Neuron 3899 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: 1.0575. Min Range: -1.0575

Max Act: 1.0109. Min Act: -0.0000

Data Index: 737888 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.0575. Min Range: -1.0575

Max Act: 1.0575. Min Act: -0.0000

Data Index: 861082 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.9761. Min Act: -0.0000

Data Index: 761277 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.7211. Min Act: 0.0000

Data Index: 1356529 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.7283. Min Act: -0.0000

Data Index: 974844 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.7849. Min Act: -0.0000

Data Index: 84846 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1050701 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6839. Min Act: 0.0000

Data Index: 384331 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6316. Min Act: -0.0000

Data Index: 40903 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6027. Min Act: -0.0000

Data Index: 652537 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6015. Min Act: -0.0000

Data Index: 692080 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.6261. Min Act: -0.0000

Data Index: 493782 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5512. Min Act: -0.0000

Data Index: 545980 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5493. Min Act: -0.0000

Data Index: 875602 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5484. Min Act: -0.0000

Data Index: 44403 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5354. Min Act: -0.0000

Data Index: 976263 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5515. Min Act: 0.0000

Data Index: 96582 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1266963 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1525096 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 1.0575. Min Range: -1.0575

Max Act: 0.5137. Min Act: -0.0000

Data Index: 621626 (C4 (Web Text))

Max Activating Token Index: 148