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

Dataset: The Pile

Neuron 1348 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1256389 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3225. Min Act: -0.0000

Data Index: 251 (The Pile)

Max Activating Token Index: 536

Text #2

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3183. Min Act: -0.0000

Data Index: 173443 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3006. Min Act: -0.0000

Data Index: 692038 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1512859 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1287058 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3123. Min Act: -0.0000

Data Index: 679906 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1486171 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1558260 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2858. Min Act: -0.0000

Data Index: 920403 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1197632 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2814. Min Act: -0.0000

Data Index: 670136 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1996173 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2682. Min Act: -0.0000

Data Index: 750295 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1649618 (The Pile)

Max Activating Token Index: 839

Text #15

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1439626 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1036484 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1492342 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1223834 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1337502 (The Pile)

Max Activating Token Index: 724