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

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

Neuron 1287 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2307. Min Range: -1.2307

Max Act: 1.2307. Min Act: -0.0000

Data Index: 239403 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.9019. Min Act: -0.0000

Data Index: 1338246 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.7936. Min Act: -0.0000

Data Index: 593696 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8235. Min Act: -0.0000

Data Index: 11642 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8591. Min Act: -0.0000

Data Index: 564544 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8025. Min Act: -0.0000

Data Index: 518574 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.7315. Min Act: -0.0000

Data Index: 525904 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.6466. Min Act: -0.0000

Data Index: 788093 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.6421. Min Act: 0.0000

Data Index: 1285858 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1043395 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.6248. Min Act: -0.0000

Data Index: 81162 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5576. Min Act: 0.0000

Data Index: 1255278 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1038123 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5543. Min Act: -0.0000

Data Index: 258612 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5184. Min Act: -0.0000

Data Index: 656341 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5529. Min Act: -0.0000

Data Index: 601034 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1303545 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5077. Min Act: -0.0000

Data Index: 172211 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5123. Min Act: -0.0000

Data Index: 542852 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5133. Min Act: -0.0000

Data Index: 850512 (C4 (Web Text))

Max Activating Token Index: 509