Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1297 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1147727 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2289. Min Act: -0.0001

Data Index: 151588 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2264. Min Act: -0.0001

Data Index: 614502 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2189. Min Act: -0.0001

Data Index: 1091435 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2107. Min Act: -0.0001

Data Index: 389137 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2090. Min Act: -0.0001

Data Index: 615072 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2006. Min Act: -0.0002

Data Index: 588873 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2065. Min Act: -0.0001

Data Index: 46152 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2054. Min Act: -0.0002

Data Index: 361266 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1927. Min Act: -0.0002

Data Index: 96227 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1912. Min Act: -0.0001

Data Index: 43891 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1925. Min Act: -0.0002

Data Index: 749322 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1980. Min Act: -0.0002

Data Index: 105914 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1961. Min Act: -0.0002

Data Index: 1175527 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1943. Min Act: -0.0001

Data Index: 480525 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1936. Min Act: -0.0002

Data Index: 992655 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1915. Min Act: -0.0002

Data Index: 688342 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1880. Min Act: -0.0001

Data Index: 101333 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1880. Min Act: -0.0002

Data Index: 943215 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1821. Min Act: -0.0001

Data Index: 439716 (C4 (Web Text))

Max Activating Token Index: 774