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

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

Neuron 3458 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2437. Min Range: -3.2437

Max Act: 3.2437. Min Act: -0.0000

Data Index: 721172 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.6716. Min Act: -0.0000

Data Index: 620169 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.9710. Min Act: -0.0000

Data Index: 502540 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.8114. Min Act: -0.0000

Data Index: 372480 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.5350. Min Act: -0.0000

Data Index: 1291721 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.7189. Min Act: -0.0000

Data Index: 311414 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.6297. Min Act: -0.0000

Data Index: 199778 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.6326. Min Act: -0.0000

Data Index: 564753 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.5027. Min Act: -0.0000

Data Index: 884686 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.3892. Min Act: -0.0000

Data Index: 110661 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.2558. Min Act: -0.0000

Data Index: 800734 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.0788. Min Act: -0.0000

Data Index: 132691 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.1302. Min Act: -0.0000

Data Index: 1166481 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.3104. Min Act: -0.0000

Data Index: 148309 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.1347. Min Act: -0.0000

Data Index: 1275560 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.2186. Min Act: -0.0000

Data Index: 592501 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.1779. Min Act: -0.0000

Data Index: 866083 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 3.2437. Min Range: -3.2437

Max Act: 1.9325. Min Act: -0.0000

Data Index: 320314 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 3.2437. Min Range: -3.2437

Max Act: 2.0522. Min Act: -0.0000

Data Index: 1181697 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.2437. Min Range: -3.2437

Max Act: 1.7503. Min Act: -0.0001

Data Index: 1491960 (Python Code)

Max Activating Token Index: 726