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

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

Neuron 1445 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2903. Min Act: -0.0000

Data Index: 685373 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2400. Min Act: -0.0000

Data Index: 461938 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2502. Min Act: -0.0000

Data Index: 767828 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2425. Min Act: -0.0000

Data Index: 586693 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1069749 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2331. Min Act: -0.0000

Data Index: 622506 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1192485 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2218. Min Act: -0.0000

Data Index: 815256 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2199. Min Act: -0.0000

Data Index: 246933 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2127. Min Act: -0.0000

Data Index: 586525 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2126. Min Act: -0.0000

Data Index: 198827 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2133. Min Act: -0.0000

Data Index: 320419 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1312289 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2089. Min Act: -0.0000

Data Index: 608590 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2140. Min Act: -0.0000

Data Index: 108402 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2074. Min Act: -0.0000

Data Index: 112606 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1881. Min Act: -0.0000

Data Index: 449498 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1198853 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2066. Min Act: -0.0000

Data Index: 36750 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.1912. Min Act: -0.0000

Data Index: 45086 (C4 (Web Text))

Max Activating Token Index: 937