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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 205 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1417363 (Python Code)

Max Activating Token Index: 637

Text #1

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1485449 (Python Code)

Max Activating Token Index: 532

Text #2

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1362313 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1634461 (Python Code)

Max Activating Token Index: 433

Text #4

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4755. Min Act: -0.0000

Data Index: 720016 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1492957 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1575239 (Python Code)

Max Activating Token Index: 359

Text #7

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1323528 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4617. Min Act: -0.0000

Data Index: 618026 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1620335 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1301098 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4395. Min Act: -0.0000

Data Index: 455302 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1416744 (Python Code)

Max Activating Token Index: 63

Text #13

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1256944 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1139474 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1431839 (Python Code)

Max Activating Token Index: 107

Text #16

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1474537 (Python Code)

Max Activating Token Index: 363

Text #17

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1154864 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3786. Min Act: -0.0000

Data Index: 611714 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1388054 (Python Code)

Max Activating Token Index: 260