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

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

Neuron 4931 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.8522. Min Act: -0.0000

Data Index: 1289441 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.5839. Min Act: -0.0000

Data Index: 1274385 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.3514. Min Act: -0.0000

Data Index: 1212397 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.5342. Min Act: -0.0000

Data Index: 918924 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.3514. Min Act: -0.0000

Data Index: 151200 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.4279. Min Act: -0.0000

Data Index: 1167834 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.4220. Min Act: -0.0000

Data Index: 662742 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.1609. Min Act: -0.0000

Data Index: 1072664 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.2477. Min Act: -0.0000

Data Index: 445451 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.2472. Min Act: -0.0000

Data Index: 921019 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.2326. Min Act: -0.0000

Data Index: 936214 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.1050. Min Act: -0.0000

Data Index: 612616 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.2035. Min Act: -0.0000

Data Index: 774736 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.1581. Min Act: -0.0000

Data Index: 623030 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.0923. Min Act: -0.0000

Data Index: 464723 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.0664. Min Act: -0.0000

Data Index: 317844 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.0521. Min Act: -0.0000

Data Index: 264073 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 2.8522. Min Range: -2.8522

Max Act: 1.9458. Min Act: -0.0000

Data Index: 735708 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 2.8522. Min Range: -2.8522

Max Act: 1.9396. Min Act: -0.0000

Data Index: 946295 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 2.8522. Min Range: -2.8522

Max Act: 2.0404. Min Act: -0.0000

Data Index: 1295450 (C4 (Web Text))

Max Activating Token Index: 263