Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3677 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0987. Min Range: -1.0987

Max Act: 1.0987. Min Act: -0.0001

Data Index: 14040 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.9155. Min Act: -0.0001

Data Index: 85589 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8808. Min Act: -0.0001

Data Index: 1126970 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8699. Min Act: -0.0001

Data Index: 850862 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8642. Min Act: -0.0001

Data Index: 1220914 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1321472 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8012. Min Act: -0.0001

Data Index: 1295033 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8135. Min Act: -0.0001

Data Index: 1161215 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7898. Min Act: -0.0001

Data Index: 52330 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7800. Min Act: -0.0001

Data Index: 375778 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7620. Min Act: -0.0001

Data Index: 1133670 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.6935. Min Act: -0.0001

Data Index: 1322408 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7013. Min Act: -0.0001

Data Index: 23758 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7891. Min Act: -0.0001

Data Index: 761232 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7353. Min Act: -0.0001

Data Index: 923853 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.8302. Min Act: -0.0001

Data Index: 953020 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7346. Min Act: -0.0001

Data Index: 949001 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7161. Min Act: -0.0001

Data Index: 835540 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7576. Min Act: -0.0001

Data Index: 240350 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.0987. Min Range: -1.0987

Max Act: 0.7221. Min Act: -0.0001

Data Index: 960965 (C4 (Web Text))

Max Activating Token Index: 713