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

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

Neuron 2244 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2989. Min Range: -2.2989

Max Act: 2.1939. Min Act: -0.0000

Data Index: 1276237 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 2.2989. Min Range: -2.2989

Max Act: 2.2989. Min Act: -0.0000

Data Index: 735198 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 2.2989. Min Range: -2.2989

Max Act: 2.1781. Min Act: -0.0001

Data Index: 1217604 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 2.2989. Min Range: -2.2989

Max Act: 2.1554. Min Act: -0.0000

Data Index: 124202 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 2.2989. Min Range: -2.2989

Max Act: 2.0896. Min Act: -0.0000

Data Index: 680052 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 2.2989. Min Range: -2.2989

Max Act: 2.0818. Min Act: -0.0000

Data Index: 102232 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.9475. Min Act: -0.0000

Data Index: 586060 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 2.2989. Min Range: -2.2989

Max Act: 2.0347. Min Act: -0.0000

Data Index: 961504 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 2.2989. Min Range: -2.2989

Max Act: 2.0103. Min Act: -0.0000

Data Index: 1096321 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.8408. Min Act: -0.0000

Data Index: 759416 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.9488. Min Act: -0.0000

Data Index: 672916 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.8232. Min Act: -0.0000

Data Index: 568337 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.6114. Min Act: -0.0000

Data Index: 899578 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.7040. Min Act: -0.0000

Data Index: 130555 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.6980. Min Act: -0.0000

Data Index: 870235 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.7698. Min Act: -0.0000

Data Index: 150999 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.7615. Min Act: -0.0000

Data Index: 4981 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.7450. Min Act: -0.0001

Data Index: 7108 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.7290. Min Act: -0.0000

Data Index: 280148 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 2.2989. Min Range: -2.2989

Max Act: 1.6318. Min Act: -0.0000

Data Index: 875967 (C4 (Web Text))

Max Activating Token Index: 804