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

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

Neuron 207 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: 1.7639. Min Range: -1.7639

Max Act: 1.7639. Min Act: -0.0000

Data Index: 227829 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.5163. Min Act: -0.0001

Data Index: 1031265 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.5105. Min Act: -0.0000

Data Index: 228671 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.3609. Min Act: -0.0000

Data Index: 969901 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1013304 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1321510 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1743. Min Act: -0.0000

Data Index: 1166093 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1208011 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1712. Min Act: -0.0001

Data Index: 433354 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.0888. Min Act: -0.0000

Data Index: 97564 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2951. Min Act: -0.0000

Data Index: 62052 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2082. Min Act: -0.0000

Data Index: 971943 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1294. Min Act: -0.0000

Data Index: 798063 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.4126. Min Act: -0.0000

Data Index: 627034 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2261. Min Act: -0.0000

Data Index: 800311 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.4559. Min Act: -0.0000

Data Index: 243738 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1396. Min Act: -0.0001

Data Index: 360712 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.0458. Min Act: -0.0000

Data Index: 450323 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.0843. Min Act: -0.0000

Data Index: 178966 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.0942. Min Act: -0.0000

Data Index: 129606 (C4 (Web Text))

Max Activating Token Index: 632