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

Dataset: The Pile

Neuron 454 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1944905 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1247403 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1597095 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1346271 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.7777. Min Act: -0.0000

Data Index: 914717 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1675922 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1726759 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1055448 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5712. Min Act: -0.0000

Data Index: 382723 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1470979 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.4940. Min Act: -0.0000

Data Index: 882505 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5684. Min Act: -0.0000

Data Index: 87012 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1729390 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1854470 (The Pile)

Max Activating Token Index: 885

Text #14

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5346. Min Act: -0.0000

Data Index: 756821 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5513. Min Act: -0.0000

Data Index: 545484 (The Pile)

Max Activating Token Index: 546

Text #16

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1780520 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1558490 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1451104 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.7777. Min Range: -0.7777

Max Act: 0.5349. Min Act: -0.0000

Data Index: 951617 (The Pile)

Max Activating Token Index: 803