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

Dataset: The Pile

Neuron 4422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1161322 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5520. Min Act: -0.0000

Data Index: 805006 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1118700 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1381384 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1078502 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4945. Min Act: -0.0000

Data Index: 788869 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4507. Min Act: -0.0000

Data Index: 893554 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4248. Min Act: -0.0000

Data Index: 630616 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1386231 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1578489 (The Pile)

Max Activating Token Index: 749

Text #10

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3913. Min Act: -0.0000

Data Index: 932502 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1308767 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1103565 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1557582 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1512560 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1346981 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.4032. Min Act: -0.0000

Data Index: 258353 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3650. Min Act: -0.0000

Data Index: 951787 (The Pile)

Max Activating Token Index: 319

Text #18

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1639981 (The Pile)

Max Activating Token Index: 972

Text #19

Max Range: 0.5520. Min Range: -0.5520

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1583201 (The Pile)

Max Activating Token Index: 962