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

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

Neuron 2359 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.4235. Min Act: -0.0000

Data Index: 393266 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1150753 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.2366. Min Act: -0.0000

Data Index: 809117 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.1816. Min Act: -0.0000

Data Index: 1318709 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.1840. Min Act: -0.0000

Data Index: 46159 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.0851. Min Act: -0.0000

Data Index: 85279 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1027937 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.1155. Min Act: -0.0000

Data Index: 979642 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.0116. Min Act: -0.0000

Data Index: 417404 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.0291. Min Act: -0.0000

Data Index: 341634 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.0965. Min Act: -0.0000

Data Index: 942061 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1192305 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 1.4235. Min Range: -1.4235

Max Act: 0.9952. Min Act: -0.0000

Data Index: 275640 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.4235. Min Range: -1.4235

Max Act: 0.9352. Min Act: -0.0000

Data Index: 298484 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1288284 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.4235. Min Range: -1.4235

Max Act: 1.0731. Min Act: -0.0000

Data Index: 5850 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 1.4235. Min Range: -1.4235

Max Act: 0.9747. Min Act: -0.0000

Data Index: 962473 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.4235. Min Range: -1.4235

Max Act: 0.9239. Min Act: -0.0000

Data Index: 331718 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.4235. Min Range: -1.4235

Max Act: 0.9987. Min Act: -0.0000

Data Index: 667264 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.4235. Min Range: -1.4235

Max Act: 0.9487. Min Act: -0.0000

Data Index: 534146 (C4 (Web Text))

Max Activating Token Index: 383