Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2918 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2883. Min Act: -0.0000

Data Index: 52809 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1166815 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1759783 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1805042 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2494. Min Act: -0.0000

Data Index: 949022 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2559. Min Act: -0.0000

Data Index: 722166 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1434207 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2447. Min Act: -0.0000

Data Index: 469127 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1366796 (The Pile)

Max Activating Token Index: 417

Text #9

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1156261 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1043308 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2568. Min Act: -0.0000

Data Index: 808199 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1455067 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2455. Min Act: -0.0000

Data Index: 714532 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2551. Min Act: -0.0000

Data Index: 656307 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2463. Min Act: -0.0000

Data Index: 233411 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2355. Min Act: -0.0000

Data Index: 982731 (The Pile)

Max Activating Token Index: 434

Text #17

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2491. Min Act: -0.0000

Data Index: 425019 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1899700 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2294. Min Act: -0.0000

Data Index: 686736 (The Pile)

Max Activating Token Index: 513