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

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

Neuron 276 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: 2.1114. Min Range: -2.1114

Max Act: 2.1114. Min Act: -0.0000

Data Index: 429816 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.0745. Min Act: -0.0000

Data Index: 1358026 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.0952. Min Act: -0.0000

Data Index: 627884 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.0692. Min Act: -0.0000

Data Index: 18502 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.0369. Min Act: -0.0000

Data Index: 898296 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.0373. Min Act: -0.0000

Data Index: 1152952 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.0272. Min Act: -0.0000

Data Index: 417953 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.0262. Min Act: -0.0000

Data Index: 46589 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.0077. Min Act: -0.0000

Data Index: 714827 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 2.1114. Min Range: -2.1114

Max Act: 2.1009. Min Act: -0.0000

Data Index: 593563 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.9676. Min Act: -0.0000

Data Index: 607444 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.8550. Min Act: -0.0000

Data Index: 1236286 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.9371. Min Act: -0.0000

Data Index: 837242 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1359460 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.8259. Min Act: -0.0000

Data Index: 265129 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.8106. Min Act: -0.0000

Data Index: 564878 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.8570. Min Act: -0.0000

Data Index: 572447 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.8401. Min Act: -0.0000

Data Index: 1000329 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.9560. Min Act: -0.0000

Data Index: 424369 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 2.1114. Min Range: -2.1114

Max Act: 1.7516. Min Act: -0.0000

Data Index: 1235514 (C4 (Web Text))

Max Activating Token Index: 405