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

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

Neuron 1895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1993. Min Range: -5.1993

Max Act: 5.1993. Min Act: -0.0000

Data Index: 1274502 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.3041. Min Act: -0.0000

Data Index: 982677 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 5.1993. Min Range: -5.1993

Max Act: 4.3278. Min Act: -0.0000

Data Index: 1337696 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.9204. Min Act: -0.0000

Data Index: 1206145 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.8303. Min Act: -0.0000

Data Index: 828351 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.8675. Min Act: -0.0000

Data Index: 394161 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.8656. Min Act: -0.0000

Data Index: 1349375 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.8437. Min Act: -0.0000

Data Index: 945539 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.7676. Min Act: -0.0000

Data Index: 176589 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.7150. Min Act: -0.0000

Data Index: 971220 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.5302. Min Act: -0.0000

Data Index: 102971 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.4885. Min Act: -0.0000

Data Index: 83369 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.3355. Min Act: -0.0000

Data Index: 698119 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.3714. Min Act: -0.0000

Data Index: 1005411 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.3664. Min Act: -0.0000

Data Index: 1353046 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.4778. Min Act: -0.0000

Data Index: 644535 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.2355. Min Act: -0.0000

Data Index: 1041251 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.3830. Min Act: -0.0000

Data Index: 480879 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.2009. Min Act: -0.0000

Data Index: 901220 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 5.1993. Min Range: -5.1993

Max Act: 3.1979. Min Act: -0.0000

Data Index: 448877 (C4 (Web Text))

Max Activating Token Index: 307