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

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

Neuron 3936 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: 5.6829. Min Range: -5.6829

Max Act: 5.6829. Min Act: -0.0000

Data Index: 289623 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 5.6829. Min Range: -5.6829

Max Act: 5.1511. Min Act: -0.0000

Data Index: 559120 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 5.6829. Min Range: -5.6829

Max Act: 5.0523. Min Act: -0.0000

Data Index: 901972 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.9222. Min Act: -0.0000

Data Index: 936634 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.7049. Min Act: -0.0000

Data Index: 654056 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.6540. Min Act: -0.0000

Data Index: 568241 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.9745. Min Act: -0.0000

Data Index: 639744 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.0842. Min Act: -0.0000

Data Index: 225545 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.2596. Min Act: -0.0000

Data Index: 1192630 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.1901. Min Act: -0.0000

Data Index: 891294 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.3304. Min Act: -0.0000

Data Index: 419036 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.7667. Min Act: -0.0000

Data Index: 752770 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.9301. Min Act: -0.0000

Data Index: 1597847 (Python Code)

Max Activating Token Index: 435

Text #13

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.7665. Min Act: -0.0000

Data Index: 1439956 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.0912. Min Act: -0.0000

Data Index: 1004282 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.8317. Min Act: -0.0000

Data Index: 392078 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.6363. Min Act: -0.0000

Data Index: 638880 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.8097. Min Act: -0.0000

Data Index: 545935 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.7377. Min Act: -0.0000

Data Index: 708027 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.7606. Min Act: -0.0000

Data Index: 944790 (C4 (Web Text))

Max Activating Token Index: 911