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

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

Neuron 1231 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1654514 (Python Code)

Max Activating Token Index: 422

Text #1

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1603907 (Python Code)

Max Activating Token Index: 877

Text #2

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1637254 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0480. Min Act: -0.0002

Data Index: 583958 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0480. Min Act: -0.0002

Data Index: 154344 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1410679 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0460. Min Act: -0.0002

Data Index: 773608 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1036509 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0454. Min Act: -0.0002

Data Index: 970812 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1541521 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1239065 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1448112 (Python Code)

Max Activating Token Index: 192

Text #12

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1521846 (Python Code)

Max Activating Token Index: 344

Text #13

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0430. Min Act: -0.0002

Data Index: 399740 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1410826 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1574094 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1342923 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0399. Min Act: -0.0002

Data Index: 753152 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0413. Min Act: -0.0002

Data Index: 324577 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0498. Min Range: -0.0498

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1426153 (Python Code)

Max Activating Token Index: 789