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

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

Neuron 630 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: 0.8709. Min Range: -0.8709

Max Act: 0.7891. Min Act: -0.0001

Data Index: 1072678 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8556. Min Act: -0.0001

Data Index: 1150983 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1136659 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7869. Min Act: -0.0001

Data Index: 1042909 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8001. Min Act: -0.0001

Data Index: 1132861 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8709. Min Act: -0.0001

Data Index: 770725 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8097. Min Act: -0.0001

Data Index: 883019 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7677. Min Act: -0.0001

Data Index: 853978 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7748. Min Act: -0.0001

Data Index: 213931 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7466. Min Act: -0.0001

Data Index: 1044937 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7643. Min Act: -0.0001

Data Index: 960216 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7093. Min Act: -0.0001

Data Index: 199811 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7623. Min Act: -0.0001

Data Index: 997777 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8065. Min Act: -0.0001

Data Index: 889032 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1052224 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7510. Min Act: -0.0001

Data Index: 656883 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7450. Min Act: -0.0001

Data Index: 175688 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7650. Min Act: -0.0001

Data Index: 1313206 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7362. Min Act: -0.0001

Data Index: 401511 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7326. Min Act: -0.0001

Data Index: 616664 (C4 (Web Text))

Max Activating Token Index: 93