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

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

Neuron 535 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.1574. Min Act: -0.0001

Data Index: 112781 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.1152. Min Act: -0.0001

Data Index: 591287 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.1087. Min Act: -0.0001

Data Index: 363728 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.7618. Min Act: -0.0001

Data Index: 1161662 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8267. Min Act: -0.0001

Data Index: 592273 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0061. Min Act: -0.0001

Data Index: 1338894 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0053. Min Act: -0.0001

Data Index: 161146 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8981. Min Act: -0.0001

Data Index: 38822 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8285. Min Act: -0.0001

Data Index: 105569 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9521. Min Act: -0.0001

Data Index: 1124709 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8781. Min Act: -0.0001

Data Index: 337304 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9380. Min Act: -0.0001

Data Index: 1194099 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8482. Min Act: -0.0001

Data Index: 518644 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9292. Min Act: -0.0001

Data Index: 41024 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8396. Min Act: -0.0001

Data Index: 1155001 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.7891. Min Act: -0.0001

Data Index: 1086875 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8518. Min Act: -0.0001

Data Index: 633442 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8383. Min Act: -0.0001

Data Index: 306475 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9037. Min Act: -0.0001

Data Index: 389337 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8402. Min Act: -0.0001

Data Index: 643621 (C4 (Web Text))

Max Activating Token Index: 621