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

Dataset: The Pile

Neuron 502 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: 3.5510. Min Range: -3.5510

Max Act: 3.5510. Min Act: -0.0000

Data Index: 777790 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 3.5510. Min Range: -3.5510

Max Act: 3.0503. Min Act: -0.0000

Data Index: 1145385 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.7832. Min Act: -0.0000

Data Index: 1044456 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 3.5510. Min Range: -3.5510

Max Act: 3.0169. Min Act: -0.0000

Data Index: 762993 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.6579. Min Act: -0.0000

Data Index: 468533 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.5900. Min Act: -0.0000

Data Index: 452526 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.5505. Min Act: -0.0000

Data Index: 1420691 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.5985. Min Act: -0.0000

Data Index: 943548 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.4237. Min Act: -0.0000

Data Index: 1264147 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.4306. Min Act: -0.0000

Data Index: 945210 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.3355. Min Act: -0.0000

Data Index: 1469318 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.3248. Min Act: -0.0000

Data Index: 43817 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 3.5510. Min Range: -3.5510

Max Act: 1.7930. Min Act: -0.0000

Data Index: 1623778 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.3125. Min Act: -0.0000

Data Index: 1507384 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.4171. Min Act: -0.0000

Data Index: 1456422 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.1629. Min Act: -0.0000

Data Index: 1950517 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.0182. Min Act: -0.0000

Data Index: 1175002 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.2123. Min Act: -0.0000

Data Index: 655439 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.0849. Min Act: -0.0000

Data Index: 262238 (The Pile)

Max Activating Token Index: 778

Text #19

Max Range: 3.5510. Min Range: -3.5510

Max Act: 2.0941. Min Act: -0.0000

Data Index: 1932578 (The Pile)

Max Activating Token Index: 991