Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4272 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.7548. Min Act: -0.0000

Data Index: 880039 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.6977. Min Act: -0.0000

Data Index: 85176 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.4768. Min Act: 0.0000

Data Index: 1080270 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2846. Min Act: -0.0000

Data Index: 131046 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.3630. Min Act: -0.0000

Data Index: 644530 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.3088. Min Act: -0.0000

Data Index: 460735 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.4014. Min Act: -0.0000

Data Index: 115668 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1337991 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2751. Min Act: -0.0000

Data Index: 68301 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2664. Min Act: -0.0000

Data Index: 57709 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2708. Min Act: -0.0000

Data Index: 567783 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2711. Min Act: -0.0000

Data Index: 481619 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.1645. Min Act: 0.0000

Data Index: 626069 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1200507 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.1873. Min Act: -0.0000

Data Index: 958839 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1049750 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.2951. Min Act: -0.0000

Data Index: 239495 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.0974. Min Act: -0.0000

Data Index: 620966 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1005780 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 1.7548. Min Range: -1.7548

Max Act: 1.1130. Min Act: -0.0000

Data Index: 380403 (C4 (Web Text))

Max Activating Token Index: 275