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

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

Neuron 123 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1566078 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.1078. Min Act: -0.0000

Data Index: 789576 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1154842 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9626. Min Act: 0.0000

Data Index: 345027 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8578. Min Act: -0.0000

Data Index: 779721 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1072664 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1027562 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1439373 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8167. Min Act: -0.0000

Data Index: 937142 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7847. Min Act: -0.0000

Data Index: 590806 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1208097 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1398150 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1544207 (Python Code)

Max Activating Token Index: 891

Text #13

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1408828 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1532226 (Python Code)

Max Activating Token Index: 721

Text #15

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1554036 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1136986 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7355. Min Act: -0.0000

Data Index: 718909 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7264. Min Act: 0.0000

Data Index: 1327440 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7545. Min Act: -0.0000

Data Index: 648638 (C4 (Web Text))

Max Activating Token Index: 540