Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2011 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.4585. Min Act: -0.0000

Data Index: 88517 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.4141. Min Act: -0.0000

Data Index: 795005 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.2514. Min Act: -0.0000

Data Index: 277963 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.1794. Min Act: -0.0000

Data Index: 378510 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0435. Min Act: -0.0000

Data Index: 375827 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.2006. Min Act: -0.0000

Data Index: 405247 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0439. Min Act: -0.0000

Data Index: 36434 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1015862 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.1035. Min Act: -0.0000

Data Index: 534592 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1349733 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1036420 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0392. Min Act: -0.0000

Data Index: 126418 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0463. Min Act: -0.0000

Data Index: 686438 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.9365. Min Act: -0.0000

Data Index: 876972 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.4585. Min Range: -1.4585

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1327237 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1206853 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1087507 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.8942. Min Act: -0.0000

Data Index: 191221 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1242882 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.4585. Min Range: -1.4585

Max Act: 0.9028. Min Act: -0.0000

Data Index: 47904 (C4 (Web Text))

Max Activating Token Index: 114