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

Dataset: The Pile

Neuron 103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2950. Min Act: -0.0000

Data Index: 551858 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1617184 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1752916 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2829. Min Act: -0.0000

Data Index: 164794 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1646914 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2734. Min Act: -0.0000

Data Index: 922231 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2621. Min Act: -0.0000

Data Index: 559028 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1670935 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1079882 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1435522 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2620. Min Act: -0.0000

Data Index: 423819 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1580464 (The Pile)

Max Activating Token Index: 233

Text #12

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2513. Min Act: -0.0000

Data Index: 186273 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1542932 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2408. Min Act: -0.0000

Data Index: 575253 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2829. Min Act: -0.0000

Data Index: 432030 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1530100 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2691. Min Act: -0.0000

Data Index: 192281 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2520. Min Act: -0.0000

Data Index: 233425 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2510. Min Act: -0.0000

Data Index: 345795 (The Pile)

Max Activating Token Index: 64