Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 215 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2436. Min Act: -0.0001

Data Index: 118574 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2286. Min Act: -0.0001

Data Index: 1089273 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1175177 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2152. Min Act: -0.0001

Data Index: 661033 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2137. Min Act: -0.0001

Data Index: 856546 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1937. Min Act: -0.0001

Data Index: 973456 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1995. Min Act: -0.0001

Data Index: 787527 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2048. Min Act: -0.0001

Data Index: 942547 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1968. Min Act: -0.0001

Data Index: 349622 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2015. Min Act: -0.0001

Data Index: 140617 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1119361 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2002. Min Act: -0.0001

Data Index: 215326 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2071. Min Act: -0.0001

Data Index: 896378 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1787. Min Act: -0.0001

Data Index: 942585 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1255674 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1901. Min Act: -0.0001

Data Index: 214496 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.2105. Min Act: -0.0001

Data Index: 1062662 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1887. Min Act: -0.0001

Data Index: 914875 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1930. Min Act: -0.0001

Data Index: 135839 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.2436. Min Range: -0.2436

Max Act: 0.1944. Min Act: -0.0001

Data Index: 1286442 (C4 (Web Text))

Max Activating Token Index: 190