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

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

Neuron 3179 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.9915. Min Act: -0.0000

Data Index: 802819 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.7808. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 5.1234. Min Range: -5.1234

Max Act: 5.1234. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.7586. Min Act: -0.0000

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.4450. Min Act: -0.0000

Data Index: 1478475 (Python Code)

Max Activating Token Index: 1021

Text #5

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.4236. Min Act: -0.0000

Data Index: 140429 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 5.1234. Min Range: -5.1234

Max Act: 4.1998. Min Act: -0.0000

Data Index: 928164 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.9434. Min Act: -0.0000

Data Index: 271816 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.7214. Min Act: -0.0000

Data Index: 564558 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8500. Min Act: -0.0000

Data Index: 641307 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8526. Min Act: -0.0000

Data Index: 1223418 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.3550. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.5279. Min Act: -0.0000

Data Index: 912232 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.8197. Min Act: -0.0000

Data Index: 32052 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.7912. Min Act: -0.0000

Data Index: 658939 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.0018. Min Act: -0.0000

Data Index: 985243 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.2505. Min Act: -0.0000

Data Index: 632428 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.3984. Min Act: -0.0000

Data Index: 1273765 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.4887. Min Act: -0.0000

Data Index: 191658 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 5.1234. Min Range: -5.1234

Max Act: 3.3076. Min Act: -0.0000

Data Index: 99615 (C4 (Web Text))

Max Activating Token Index: 570