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

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

Neuron 4124 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.6233. Min Act: -0.0000

Data Index: 736239 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.6608. Min Act: -0.0000

Data Index: 931995 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5159. Min Act: -0.0000

Data Index: 867843 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.6013. Min Act: -0.0000

Data Index: 850294 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1133268 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5603. Min Act: -0.0000

Data Index: 856049 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5641. Min Act: -0.0000

Data Index: 847373 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5511. Min Act: -0.0000

Data Index: 982739 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1254524 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5174. Min Act: 0.0000

Data Index: 944380 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5304. Min Act: -0.0000

Data Index: 259088 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4990. Min Act: -0.0000

Data Index: 633146 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4950. Min Act: -0.0000

Data Index: 155934 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1164760 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1157202 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.5062. Min Act: -0.0000

Data Index: 336393 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1228805 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1067386 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4672. Min Act: -0.0000

Data Index: 256331 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.6608. Min Range: -0.6608

Max Act: 0.4747. Min Act: 0.0000

Data Index: 585200 (C4 (Web Text))

Max Activating Token Index: 241