Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1516 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.5647. Min Act: -0.0000

Data Index: 719096 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.7158. Min Act: -0.0000

Data Index: 739614 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4563. Min Act: -0.0000

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4668. Min Act: -0.0000

Data Index: 809192 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.4158. Min Act: -0.0000

Data Index: 595530 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3852. Min Act: -0.0000

Data Index: 98546 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3416. Min Act: -0.0000

Data Index: 446884 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1332272 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1200711 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1175946 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2982. Min Act: -0.0000

Data Index: 505072 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2046. Min Act: -0.0000

Data Index: 294237 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2457. Min Act: -0.0000

Data Index: 1183084 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2790. Min Act: -0.0000

Data Index: 561221 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.0547. Min Act: -0.0000

Data Index: 321838 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.0888. Min Act: -0.0000

Data Index: 797463 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.2293. Min Act: -0.0000

Data Index: 236063 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.0572. Min Act: -0.0000

Data Index: 170785 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.0600. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.7158. Min Range: -1.7158

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1244206 (C4 (Web Text))

Max Activating Token Index: 470