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

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

Neuron 3322 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.6308. Min Act: -0.0000

Data Index: 148005 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.5304. Min Act: -0.0000

Data Index: 393855 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4490. Min Act: -0.0000

Data Index: 534173 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.1121. Min Act: -0.0000

Data Index: 785281 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1258822 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.1820. Min Act: -0.0000

Data Index: 926674 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.2206. Min Act: -0.0000

Data Index: 1107434 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.0443. Min Act: -0.0000

Data Index: 324929 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1242357 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.9890. Min Act: -0.0000

Data Index: 415557 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.1503. Min Act: -0.0000

Data Index: 883622 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.9429. Min Act: -0.0001

Data Index: 1218179 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.7701. Min Act: -0.0000

Data Index: 199721 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1171157 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.7997. Min Act: -0.0001

Data Index: 679188 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.6728. Min Act: -0.0000

Data Index: 155088 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.8010. Min Act: -0.0000

Data Index: 839619 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.6990. Min Act: -0.0000

Data Index: 585971 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1086164 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.6308. Min Range: -1.6308

Max Act: 0.8116. Min Act: -0.0000

Data Index: 306861 (C4 (Web Text))

Max Activating Token Index: 323