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

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

Neuron 4692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.7231. Min Act: -0.0000

Data Index: 956297 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.9695. Min Act: -0.0000

Data Index: 700112 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.6747. Min Act: -0.0000

Data Index: 881217 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.9100. Min Act: -0.0000

Data Index: 545522 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.9099. Min Act: -0.0000

Data Index: 580322 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.8907. Min Act: -0.0000

Data Index: 606524 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.7334. Min Act: -0.0000

Data Index: 1027698 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.8635. Min Act: -0.0000

Data Index: 1279742 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.7126. Min Act: -0.0000

Data Index: 103379 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.6689. Min Act: -0.0000

Data Index: 1001071 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.6253. Min Act: -0.0000

Data Index: 699062 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.5093. Min Act: -0.0000

Data Index: 19142 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.6327. Min Act: -0.0000

Data Index: 262500 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.5225. Min Act: -0.0000

Data Index: 366045 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.4437. Min Act: -0.0000

Data Index: 534582 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.6035. Min Act: -0.0000

Data Index: 59344 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.3747. Min Act: -0.0000

Data Index: 354535 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.8582. Min Act: -0.0000

Data Index: 576847 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.5735. Min Act: -0.0000

Data Index: 1188109 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 2.9695. Min Range: -2.9695

Max Act: 2.6282. Min Act: -0.0000

Data Index: 712515 (C4 (Web Text))

Max Activating Token Index: 493