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

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

Neuron 3560 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.8848. Min Act: -0.0000

Data Index: 10318 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.8504. Min Act: -0.0000

Data Index: 641304 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.8587. Min Act: -0.0001

Data Index: 1209151 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7823. Min Act: -0.0000

Data Index: 542247 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1104973 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7396. Min Act: -0.0000

Data Index: 2764 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1289982 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7525. Min Act: -0.0001

Data Index: 533945 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7068. Min Act: -0.0001

Data Index: 1139864 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7008. Min Act: -0.0001

Data Index: 474932 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6857. Min Act: -0.0000

Data Index: 431185 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7228. Min Act: -0.0000

Data Index: 353530 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7191. Min Act: -0.0001

Data Index: 876683 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7152. Min Act: -0.0001

Data Index: 313563 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7217. Min Act: -0.0001

Data Index: 95609 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6850. Min Act: -0.0000

Data Index: 311285 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.7100. Min Act: -0.0001

Data Index: 1327751 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6592. Min Act: -0.0001

Data Index: 931634 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6520. Min Act: -0.0001

Data Index: 548331 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.8848. Min Range: -0.8848

Max Act: 0.6766. Min Act: -0.0000

Data Index: 611453 (C4 (Web Text))

Max Activating Token Index: 259