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

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

Neuron 421 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.7363. Min Act: -0.0000

Data Index: 263632 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.4731. Min Act: -0.0000

Data Index: 1213915 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.2270. Min Act: -0.0000

Data Index: 179946 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.2089. Min Act: -0.0000

Data Index: 562761 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.8778. Min Act: -0.0000

Data Index: 1082234 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.1348. Min Act: -0.0000

Data Index: 858591 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.0886. Min Act: -0.0000

Data Index: 94645 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.0827. Min Act: -0.0000

Data Index: 630535 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.0671. Min Act: -0.0000

Data Index: 454829 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.9331. Min Act: -0.0000

Data Index: 1281109 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.2077. Min Act: -0.0000

Data Index: 601179 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.7938. Min Act: -0.0000

Data Index: 488796 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.9759. Min Act: -0.0000

Data Index: 385346 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.0424. Min Act: -0.0000

Data Index: 817710 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.8213. Min Act: -0.0000

Data Index: 321056 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.7147. Min Act: -0.0000

Data Index: 807416 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.8105. Min Act: -0.0000

Data Index: 1345431 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 2.7363. Min Range: -2.7363

Max Act: 2.0821. Min Act: -0.0000

Data Index: 420287 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.7957. Min Act: -0.0000

Data Index: 1300697 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 2.7363. Min Range: -2.7363

Max Act: 1.8644. Min Act: -0.0000

Data Index: 731343 (C4 (Web Text))

Max Activating Token Index: 12