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

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

Neuron 1243 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9200. Min Range: -4.9200

Max Act: 4.4100. Min Act: -0.0000

Data Index: 926459 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 4.9200. Min Range: -4.9200

Max Act: 4.9200. Min Act: -0.0000

Data Index: 125101 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 4.9200. Min Range: -4.9200

Max Act: 4.0416. Min Act: -0.0000

Data Index: 856465 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.4202. Min Act: -0.0000

Data Index: 20686 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.5320. Min Act: -0.0000

Data Index: 361892 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.4019. Min Act: -0.0000

Data Index: 904365 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.3356. Min Act: -0.0000

Data Index: 236287 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.3041. Min Act: -0.0000

Data Index: 938672 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.2611. Min Act: -0.0000

Data Index: 1002488 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.3744. Min Act: -0.0000

Data Index: 55167 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.3520. Min Act: -0.0000

Data Index: 976233 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.1800. Min Act: -0.0000

Data Index: 270233 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.0968. Min Act: -0.0000

Data Index: 452925 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.1526. Min Act: -0.0000

Data Index: 662686 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.3008. Min Act: -0.0000

Data Index: 415626 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.2484. Min Act: -0.0000

Data Index: 8654 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.3577. Min Act: -0.0000

Data Index: 11941 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.1978. Min Act: -0.0000

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.3957. Min Act: -0.0000

Data Index: 1012781 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 4.9200. Min Range: -4.9200

Max Act: 3.2133. Min Act: -0.0000

Data Index: 1147008 (C4 (Web Text))

Max Activating Token Index: 481