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

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

Neuron 2160 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0485. Min Range: -1.0485

Max Act: 1.0485. Min Act: -0.0003

Data Index: 249246 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.9939. Min Act: -0.0003

Data Index: 118128 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.7977. Min Act: -0.0003

Data Index: 1354341 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8752. Min Act: -0.0003

Data Index: 1188572 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8184. Min Act: -0.0003

Data Index: 1169696 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8981. Min Act: -0.0003

Data Index: 859061 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.9469. Min Act: -0.0003

Data Index: 97323 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8227. Min Act: -0.0003

Data Index: 600428 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8590. Min Act: -0.0003

Data Index: 527953 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8610. Min Act: -0.0003

Data Index: 594861 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8862. Min Act: -0.0003

Data Index: 749142 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8132. Min Act: -0.0003

Data Index: 1131841 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.7943. Min Act: -0.0003

Data Index: 328390 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.7448. Min Act: -0.0003

Data Index: 207428 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8036. Min Act: -0.0003

Data Index: 381237 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8058. Min Act: -0.0003

Data Index: 990712 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.7811. Min Act: -0.0003

Data Index: 31954 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.7285. Min Act: -0.0003

Data Index: 1253531 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8181. Min Act: -0.0003

Data Index: 119914 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 1.0485. Min Range: -1.0485

Max Act: 0.8469. Min Act: -0.0003

Data Index: 464255 (C4 (Web Text))

Max Activating Token Index: 120