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

Dataset: The Pile

Neuron 5049 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: 3.8678. Min Range: -3.8678

Max Act: 3.8678. Min Act: -0.0000

Data Index: 1314177 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.2842. Min Act: -0.0000

Data Index: 976769 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 3.8678. Min Range: -3.8678

Max Act: 2.9967. Min Act: -0.0000

Data Index: 1900181 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.1185. Min Act: -0.0000

Data Index: 371216 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.0941. Min Act: -0.0000

Data Index: 1929060 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.2346. Min Act: -0.0000

Data Index: 1606440 (The Pile)

Max Activating Token Index: 314

Text #6

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.1679. Min Act: -0.0000

Data Index: 1230841 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.0182. Min Act: -0.0000

Data Index: 1801001 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.1123. Min Act: -0.0000

Data Index: 189677 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.1131. Min Act: -0.0000

Data Index: 611788 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.2436. Min Act: -0.0000

Data Index: 1592782 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.1352. Min Act: -0.0000

Data Index: 1281679 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 3.8678. Min Range: -3.8678

Max Act: 2.8350. Min Act: -0.0000

Data Index: 1403398 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.0405. Min Act: -0.0000

Data Index: 680499 (The Pile)

Max Activating Token Index: 825

Text #14

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.1366. Min Act: -0.0000

Data Index: 147822 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 3.8678. Min Range: -3.8678

Max Act: 3.0066. Min Act: -0.0000

Data Index: 861721 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 3.8678. Min Range: -3.8678

Max Act: 2.8621. Min Act: -0.0000

Data Index: 1620321 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 3.8678. Min Range: -3.8678

Max Act: 2.4584. Min Act: -0.0000

Data Index: 473451 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 3.8678. Min Range: -3.8678

Max Act: 2.9283. Min Act: -0.0000

Data Index: 224660 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 3.8678. Min Range: -3.8678

Max Act: 2.9181. Min Act: -0.0000

Data Index: 210584 (The Pile)

Max Activating Token Index: 563