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

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

Neuron 4460 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: 0.8055. Min Range: -0.8055

Max Act: 0.8055. Min Act: -0.0000

Data Index: 360015 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1127052 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1019151 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7025. Min Act: -0.0000

Data Index: 144248 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7251. Min Act: -0.0000

Data Index: 56089 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1281575 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7043. Min Act: -0.0000

Data Index: 211439 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7272. Min Act: -0.0000

Data Index: 233575 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6485. Min Act: 0.0000

Data Index: 727256 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6204. Min Act: -0.0000

Data Index: 681275 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6356. Min Act: -0.0000

Data Index: 509184 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1080866 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6553. Min Act: -0.0000

Data Index: 784770 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6232. Min Act: 0.0000

Data Index: 678869 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6435. Min Act: -0.0000

Data Index: 443480 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6454. Min Act: -0.0000

Data Index: 990212 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6503. Min Act: -0.0000

Data Index: 666894 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6323. Min Act: 0.0000

Data Index: 771283 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6264. Min Act: -0.0000

Data Index: 972272 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6559. Min Act: -0.0000

Data Index: 249698 (C4 (Web Text))

Max Activating Token Index: 879