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

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

Neuron 3496 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.7136. Min Act: -0.0000

Data Index: 249350 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6398. Min Act: -0.0000

Data Index: 954262 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.6188. Min Act: -0.0000

Data Index: 820358 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5535. Min Act: -0.0000

Data Index: 58700 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5617. Min Act: -0.0000

Data Index: 196052 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1175466 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5346. Min Act: -0.0000

Data Index: 504321 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1164596 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.5266. Min Act: -0.0000

Data Index: 894917 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4782. Min Act: -0.0000

Data Index: 108452 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4910. Min Act: -0.0000

Data Index: 14324 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4726. Min Act: -0.0000

Data Index: 482824 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1082075 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4452. Min Act: -0.0000

Data Index: 998660 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4455. Min Act: -0.0000

Data Index: 550904 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4749. Min Act: -0.0000

Data Index: 207768 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4414. Min Act: -0.0000

Data Index: 722625 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4499. Min Act: -0.0000

Data Index: 732562 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4502. Min Act: -0.0000

Data Index: 882819 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.7136. Min Range: -0.7136

Max Act: 0.4195. Min Act: -0.0000

Data Index: 217438 (C4 (Web Text))

Max Activating Token Index: 141