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

Dataset: The Pile

Neuron 744 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.1635. Min Act: -0.0000

Data Index: 1472057 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1944551 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0339. Min Act: -0.0000

Data Index: 540962 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0263. Min Act: -0.0000

Data Index: 436646 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 1.1635. Min Range: -1.1635

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1807596 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9389. Min Act: -0.0000

Data Index: 624087 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8756. Min Act: -0.0000

Data Index: 693006 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1968318 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1640175 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1017207 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8151. Min Act: -0.0000

Data Index: 964131 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8286. Min Act: -0.0000

Data Index: 893912 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8419. Min Act: -0.0000

Data Index: 770448 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8542. Min Act: -0.0000

Data Index: 381392 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1202220 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8098. Min Act: -0.0000

Data Index: 905720 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.8360. Min Act: -0.0000

Data Index: 589269 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1998955 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7519. Min Act: -0.0000

Data Index: 907410 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 1.1635. Min Range: -1.1635

Max Act: 0.7564. Min Act: -0.0000

Data Index: 206360 (The Pile)

Max Activating Token Index: 648