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

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

Neuron 6137 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.5710. Min Act: -0.0001

Data Index: 1132540 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.5839. Min Act: -0.0001

Data Index: 780753 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.5141. Min Act: -0.0001

Data Index: 414218 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.5302. Min Act: -0.0001

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.5053. Min Act: -0.0001

Data Index: 1332601 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4767. Min Act: -0.0001

Data Index: 1047667 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4354. Min Act: -0.0001

Data Index: 1150594 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4783. Min Act: -0.0001

Data Index: 452109 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4806. Min Act: -0.0001

Data Index: 403632 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4090. Min Act: -0.0001

Data Index: 795397 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3969. Min Act: -0.0001

Data Index: 914610 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4442. Min Act: -0.0000

Data Index: 885095 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4231. Min Act: -0.0001

Data Index: 1339619 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4385. Min Act: -0.0001

Data Index: 581846 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4216. Min Act: -0.0001

Data Index: 1244345 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4420. Min Act: -0.0001

Data Index: 1055037 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4292. Min Act: -0.0001

Data Index: 472356 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3997. Min Act: -0.0001

Data Index: 1152682 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.3999. Min Act: -0.0001

Data Index: 718405 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.5839. Min Range: -0.5839

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1140858 (C4 (Web Text))

Max Activating Token Index: 871