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

Dataset: The Pile

Neuron 2249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4484. Min Act: -0.0000

Data Index: 58788 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4043. Min Act: -0.0000

Data Index: 583865 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1965765 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3066. Min Act: -0.0000

Data Index: 794092 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2942. Min Act: -0.0000

Data Index: 745640 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1177025 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2993. Min Act: -0.0000

Data Index: 249359 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2761. Min Act: -0.0000

Data Index: 566857 (The Pile)

Max Activating Token Index: 966

Text #8

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2467. Min Act: -0.0000

Data Index: 7430 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1384462 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1552051 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2577. Min Act: -0.0000

Data Index: 5442 (The Pile)

Max Activating Token Index: 335

Text #12

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2620. Min Act: -0.0000

Data Index: 996794 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1407123 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1604365 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2415. Min Act: -0.0000

Data Index: 959038 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2768. Min Act: -0.0000

Data Index: 504664 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2494. Min Act: -0.0000

Data Index: 684658 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2337. Min Act: -0.0000

Data Index: 209897 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.2540. Min Act: -0.0000

Data Index: 631367 (The Pile)

Max Activating Token Index: 234