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

Dataset: The Pile

Neuron 2220 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: 3.5778. Min Range: -3.5778

Max Act: 3.5778. Min Act: -0.0000

Data Index: 1747894 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 3.5778. Min Range: -3.5778

Max Act: 3.1560. Min Act: -0.0000

Data Index: 1356443 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 3.5778. Min Range: -3.5778

Max Act: 2.4962. Min Act: -0.0000

Data Index: 70820 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 3.5778. Min Range: -3.5778

Max Act: 2.0302. Min Act: -0.0000

Data Index: 1541004 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.9580. Min Act: -0.0000

Data Index: 863632 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.9294. Min Act: -0.0000

Data Index: 365498 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.8921. Min Act: -0.0000

Data Index: 1638870 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1774667 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.7801. Min Act: -0.0000

Data Index: 1608724 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.9785. Min Act: -0.0000

Data Index: 261958 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.9715. Min Act: -0.0000

Data Index: 1403369 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.7924. Min Act: -0.0000

Data Index: 1696394 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.9189. Min Act: -0.0000

Data Index: 1615140 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.6614. Min Act: -0.0000

Data Index: 1373556 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.9976. Min Act: -0.0000

Data Index: 1127756 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.7751. Min Act: -0.0000

Data Index: 1676179 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.6939. Min Act: -0.0000

Data Index: 1304884 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.7783. Min Act: -0.0000

Data Index: 501142 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.6795. Min Act: -0.0000

Data Index: 145952 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 3.5778. Min Range: -3.5778

Max Act: 1.9199. Min Act: -0.0000

Data Index: 289023 (The Pile)

Max Activating Token Index: 738