Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 775 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2163. Min Act: -0.0001

Data Index: 510971 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1837. Min Act: -0.0001

Data Index: 309282 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1850. Min Act: -0.0001

Data Index: 524403 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1850. Min Act: -0.0001

Data Index: 969174 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1643. Min Act: -0.0001

Data Index: 431695 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1698. Min Act: -0.0000

Data Index: 443212 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1313264 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1628. Min Act: -0.0001

Data Index: 775387 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1563. Min Act: -0.0001

Data Index: 658932 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1210676 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1649. Min Act: -0.0001

Data Index: 302085 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1501. Min Act: -0.0000

Data Index: 728931 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1350483 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1215709 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1625685 (Python Code)

Max Activating Token Index: 417

Text #15

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1549390 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1256927 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1300. Min Act: -0.0001

Data Index: 785020 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1389188 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1380947 (Python Code)

Max Activating Token Index: 283