Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2617. Min Range: -2.2617

Max Act: 2.2617. Min Act: -0.0000

Data Index: 1144922 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 2.2617. Min Range: -2.2617

Max Act: 2.1055. Min Act: -0.0000

Data Index: 43215 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.9771. Min Act: -0.0001

Data Index: 953168 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.8319. Min Act: -0.0001

Data Index: 210722 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.8278. Min Act: -0.0000

Data Index: 334496 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.8295. Min Act: -0.0001

Data Index: 647077 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.8018. Min Act: -0.0001

Data Index: 615991 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.7608. Min Act: -0.0000

Data Index: 54119 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.8012. Min Act: -0.0001

Data Index: 1026444 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.7205. Min Act: -0.0000

Data Index: 789439 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.7102. Min Act: -0.0000

Data Index: 494276 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.6505. Min Act: -0.0001

Data Index: 921499 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.5858. Min Act: -0.0001

Data Index: 573404 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.5716. Min Act: -0.0000

Data Index: 970326 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.5942. Min Act: -0.0001

Data Index: 851181 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.5874. Min Act: -0.0000

Data Index: 613331 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.5900. Min Act: -0.0001

Data Index: 1151750 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.6098. Min Act: -0.0000

Data Index: 583482 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.5029. Min Act: -0.0001

Data Index: 892307 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 2.2617. Min Range: -2.2617

Max Act: 1.6128. Min Act: -0.0001

Data Index: 469839 (C4 (Web Text))

Max Activating Token Index: 964