Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1298 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4966. Min Range: -2.4966

Max Act: 2.4966. Min Act: -0.0000

Data Index: 152415 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.9261. Min Act: -0.0000

Data Index: 872012 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.6499. Min Act: -0.0000

Data Index: 116557 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.7423. Min Act: -0.0000

Data Index: 1356985 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.7529. Min Act: -0.0000

Data Index: 760689 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.7377. Min Act: -0.0000

Data Index: 1319966 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.8229. Min Act: -0.0000

Data Index: 1122861 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.6116. Min Act: -0.0000

Data Index: 120837 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.6867. Min Act: -0.0000

Data Index: 886907 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.6890. Min Act: -0.0000

Data Index: 1062588 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.6514. Min Act: -0.0000

Data Index: 781933 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1214327 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.5047. Min Act: -0.0000

Data Index: 262933 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.5318. Min Act: -0.0000

Data Index: 565916 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.4337. Min Act: -0.0000

Data Index: 796619 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.5928. Min Act: -0.0000

Data Index: 757071 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.5067. Min Act: -0.0000

Data Index: 98725 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.4942. Min Act: -0.0000

Data Index: 57024 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.4403. Min Act: -0.0000

Data Index: 700918 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 2.4966. Min Range: -2.4966

Max Act: 1.4414. Min Act: -0.0000

Data Index: 380148 (C4 (Web Text))

Max Activating Token Index: 732