Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4739 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.7045. Min Act: -0.0000

Data Index: 42402 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.7378. Min Act: -0.0000

Data Index: 139836 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.7333. Min Act: -0.0000

Data Index: 222288 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.6006. Min Act: -0.0000

Data Index: 24874 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1187444 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1271063 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.5752. Min Act: -0.0000

Data Index: 185557 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1246182 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.5218. Min Act: -0.0000

Data Index: 127060 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4696. Min Act: -0.0000

Data Index: 29592 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.5258. Min Act: -0.0000

Data Index: 908451 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4804. Min Act: -0.0000

Data Index: 313877 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4971. Min Act: -0.0000

Data Index: 40484 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4692. Min Act: -0.0000

Data Index: 460522 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4490. Min Act: -0.0000

Data Index: 527075 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.5070. Min Act: -0.0000

Data Index: 260003 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1349952 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4776. Min Act: -0.0000

Data Index: 442851 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4473. Min Act: -0.0000

Data Index: 590787 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.7378. Min Range: -0.7378

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1124822 (C4 (Web Text))

Max Activating Token Index: 289