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

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

Neuron 5295 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: 1.2344. Min Range: -1.2344

Max Act: 1.2344. Min Act: -0.0002

Data Index: 114795 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0887. Min Act: -0.0002

Data Index: 1117363 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0257. Min Act: -0.0002

Data Index: 693168 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 1.2344. Min Range: -1.2344

Max Act: 1.0132. Min Act: -0.0002

Data Index: 443737 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9532. Min Act: -0.0002

Data Index: 1148635 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9483. Min Act: -0.0002

Data Index: 2441 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9303. Min Act: -0.0002

Data Index: 849264 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9346. Min Act: -0.0002

Data Index: 223188 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9053. Min Act: -0.0002

Data Index: 1043435 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9152. Min Act: -0.0002

Data Index: 607119 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8940. Min Act: -0.0002

Data Index: 809553 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.9009. Min Act: -0.0002

Data Index: 331176 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8846. Min Act: -0.0002

Data Index: 57571 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8886. Min Act: -0.0002

Data Index: 73143 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8792. Min Act: -0.0002

Data Index: 318333 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8777. Min Act: -0.0002

Data Index: 1131100 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8619. Min Act: -0.0002

Data Index: 462978 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8764. Min Act: -0.0002

Data Index: 179107 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8618. Min Act: -0.0002

Data Index: 222610 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.2344. Min Range: -1.2344

Max Act: 0.8798. Min Act: -0.0002

Data Index: 821178 (C4 (Web Text))

Max Activating Token Index: 271