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

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

Neuron 4236 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.2892. Min Act: -0.0002

Data Index: 752763 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.2382. Min Act: -0.0002

Data Index: 1254172 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.1826. Min Act: -0.0002

Data Index: 715134 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.1743. Min Act: -0.0002

Data Index: 30683 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.2076. Min Act: -0.0002

Data Index: 777194 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.1333. Min Act: -0.0002

Data Index: 285270 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.1863. Min Act: -0.0003

Data Index: 792963 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0704. Min Act: -0.0002

Data Index: 903075 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0774. Min Act: -0.0002

Data Index: 447344 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0811. Min Act: -0.0002

Data Index: 1206795 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0976. Min Act: -0.0002

Data Index: 348735 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0394. Min Act: -0.0002

Data Index: 838156 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.1048. Min Act: -0.0002

Data Index: 1022833 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0285. Min Act: -0.0002

Data Index: 673875 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0872. Min Act: -0.0002

Data Index: 605743 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0038. Min Act: -0.0002

Data Index: 277521 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0110. Min Act: -0.0002

Data Index: 426026 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0266. Min Act: -0.0002

Data Index: 61921 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0289. Min Act: -0.0002

Data Index: 1328415 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 2.2892. Min Range: -2.2892

Max Act: 2.0481. Min Act: -0.0003

Data Index: 109086 (C4 (Web Text))

Max Activating Token Index: 390