Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1261 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1175544 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2279. Min Act: -0.0001

Data Index: 304873 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2130. Min Act: -0.0001

Data Index: 274548 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2205. Min Act: -0.0001

Data Index: 343147 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1884. Min Act: -0.0001

Data Index: 921800 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1222184 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2001. Min Act: -0.0001

Data Index: 64125 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1831. Min Act: -0.0001

Data Index: 453113 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1017824 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2035. Min Act: -0.0001

Data Index: 256597 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1528. Min Act: -0.0001

Data Index: 91108 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1332743 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1708. Min Act: -0.0001

Data Index: 524315 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1736. Min Act: -0.0000

Data Index: 573486 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1666. Min Act: -0.0001

Data Index: 229199 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1801. Min Act: -0.0001

Data Index: 774403 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1250063 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1679. Min Act: -0.0001

Data Index: 349068 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1605. Min Act: -0.0001

Data Index: 453579 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1520. Min Act: -0.0001

Data Index: 991652 (C4 (Web Text))

Max Activating Token Index: 628