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

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

Neuron 4271 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: 0.1370. Min Range: -0.1370

Max Act: 0.1343. Min Act: -0.0000

Data Index: 209732 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1370. Min Act: -0.0000

Data Index: 723194 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1204. Min Act: -0.0000

Data Index: 274492 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1179. Min Act: -0.0000

Data Index: 776527 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1103. Min Act: -0.0000

Data Index: 554096 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1223226 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1067. Min Act: -0.0000

Data Index: 552269 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1105. Min Act: -0.0000

Data Index: 246025 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1032. Min Act: -0.0000

Data Index: 419616 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.0941. Min Act: -0.0000

Data Index: 426846 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1326033 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1182983 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1018. Min Act: -0.0000

Data Index: 123393 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1040. Min Act: -0.0000

Data Index: 284227 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.0944. Min Act: -0.0000

Data Index: 83644 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1053. Min Act: -0.0000

Data Index: 194196 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.0938. Min Act: -0.0000

Data Index: 92594 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.0898. Min Act: -0.0000

Data Index: 699961 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.0996. Min Act: -0.0000

Data Index: 411270 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.0930. Min Act: -0.0000

Data Index: 322242 (C4 (Web Text))

Max Activating Token Index: 785