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

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

Neuron 1753 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.3011. Min Range: -9.3011

Max Act: 9.3011. Min Act: -0.0001

Data Index: 230759 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.7625. Min Act: -0.0001

Data Index: 1128442 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.7526. Min Act: -0.0001

Data Index: 169394 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.6496. Min Act: -0.0000

Data Index: 404604 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.6470. Min Act: -0.0000

Data Index: 1080509 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.5930. Min Act: -0.0000

Data Index: 462727 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.1517. Min Act: -0.0001

Data Index: 436410 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.4094. Min Act: -0.0000

Data Index: 827566 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.0684. Min Act: -0.0000

Data Index: 22370 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.0715. Min Act: -0.0000

Data Index: 265246 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.1935. Min Act: -0.0000

Data Index: 613023 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.1543. Min Act: -0.0000

Data Index: 1045989 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.2983. Min Act: -0.0000

Data Index: 321835 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 9.3011. Min Range: -9.3011

Max Act: 7.9245. Min Act: -0.0001

Data Index: 803856 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 9.3011. Min Range: -9.3011

Max Act: 7.8894. Min Act: -0.0000

Data Index: 846670 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.1882. Min Act: -0.0000

Data Index: 476607 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 9.3011. Min Range: -9.3011

Max Act: 8.0180. Min Act: -0.0000

Data Index: 414917 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 9.3011. Min Range: -9.3011

Max Act: 7.8579. Min Act: -0.0000

Data Index: 1030142 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 9.3011. Min Range: -9.3011

Max Act: 7.9893. Min Act: -0.0000

Data Index: 1268843 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 9.3011. Min Range: -9.3011

Max Act: 7.8320. Min Act: -0.0000

Data Index: 1317570 (C4 (Web Text))

Max Activating Token Index: 617