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

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

Neuron 3847 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.8831. Min Act: -0.0002

Data Index: 359291 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.6797. Min Act: -0.0002

Data Index: 1112240 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.6787. Min Act: -0.0002

Data Index: 664525 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.6616. Min Act: -0.0002

Data Index: 394799 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5387. Min Act: -0.0002

Data Index: 570753 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5689. Min Act: -0.0002

Data Index: 1151372 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.6363. Min Act: -0.0002

Data Index: 1165592 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5758. Min Act: -0.0002

Data Index: 869173 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5310. Min Act: -0.0002

Data Index: 196341 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5272. Min Act: -0.0002

Data Index: 1216225 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.4747. Min Act: -0.0002

Data Index: 870829 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5042. Min Act: -0.0002

Data Index: 1297497 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5373. Min Act: -0.0002

Data Index: 94175 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.4066. Min Act: -0.0002

Data Index: 47664 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.4709. Min Act: -0.0002

Data Index: 1315770 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5041. Min Act: -0.0002

Data Index: 1265024 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.5013. Min Act: -0.0002

Data Index: 960719 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.4866. Min Act: -0.0002

Data Index: 541492 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.4128. Min Act: -0.0002

Data Index: 165912 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 1.8831. Min Range: -1.8831

Max Act: 1.4431. Min Act: -0.0002

Data Index: 218795 (C4 (Web Text))

Max Activating Token Index: 50