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

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

Neuron 1177 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8594. Min Act: -0.0001

Data Index: 56331 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8618. Min Act: -0.0001

Data Index: 1252713 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8426. Min Act: -0.0001

Data Index: 1054723 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7990. Min Act: -0.0001

Data Index: 950152 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7921. Min Act: -0.0001

Data Index: 796454 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1067910 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7152. Min Act: -0.0001

Data Index: 308809 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7386. Min Act: -0.0001

Data Index: 433710 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7830. Min Act: -0.0001

Data Index: 649906 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7953. Min Act: -0.0001

Data Index: 1294192 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1138036 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.6858. Min Act: -0.0001

Data Index: 164782 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7078. Min Act: -0.0001

Data Index: 1103519 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7080. Min Act: -0.0001

Data Index: 806400 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.6744. Min Act: -0.0001

Data Index: 233741 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7144. Min Act: -0.0001

Data Index: 474381 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.6992. Min Act: -0.0001

Data Index: 144533 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.6786. Min Act: -0.0001

Data Index: 525569 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7302. Min Act: -0.0001

Data Index: 523688 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7086. Min Act: -0.0001

Data Index: 884001 (C4 (Web Text))

Max Activating Token Index: 69