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

Dataset: The Pile

Neuron 343 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.9631. Min Act: -0.0000

Data Index: 719331 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 7.1298. Min Range: -7.1298

Max Act: 7.1298. Min Act: -0.0000

Data Index: 1951011 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.9799. Min Act: -0.0000

Data Index: 157409 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.5432. Min Act: -0.0000

Data Index: 1174897 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.6461. Min Act: -0.0000

Data Index: 1991109 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.6146. Min Act: -0.0000

Data Index: 870710 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.6025. Min Act: -0.0000

Data Index: 1961849 (The Pile)

Max Activating Token Index: 392

Text #7

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.4654. Min Act: -0.0000

Data Index: 73033 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.6357. Min Act: -0.0000

Data Index: 851886 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.4326. Min Act: -0.0000

Data Index: 1519201 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.0520. Min Act: -0.0000

Data Index: 44904 (The Pile)

Max Activating Token Index: 616

Text #11

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.3932. Min Act: -0.0000

Data Index: 1218949 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.3825. Min Act: -0.0000

Data Index: 1770427 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.5427. Min Act: -0.0000

Data Index: 769384 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.3486. Min Act: -0.0000

Data Index: 1533687 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.0592. Min Act: -0.0000

Data Index: 903963 (The Pile)

Max Activating Token Index: 413

Text #16

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.4027. Min Act: -0.0000

Data Index: 146056 (The Pile)

Max Activating Token Index: 411

Text #17

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.3463. Min Act: -0.0000

Data Index: 1734655 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 7.1298. Min Range: -7.1298

Max Act: 5.9583. Min Act: -0.0000

Data Index: 1124246 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 7.1298. Min Range: -7.1298

Max Act: 6.1313. Min Act: -0.0000

Data Index: 865354 (The Pile)

Max Activating Token Index: 522