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

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

Neuron 3566 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3958. Min Range: -1.3958

Max Act: 1.3958. Min Act: -0.0000

Data Index: 186525 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 1.3958. Min Range: -1.3958

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1377671 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 1.3958. Min Range: -1.3958

Max Act: 1.3030. Min Act: -0.0000

Data Index: 345313 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.3958. Min Range: -1.3958

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1544362 (Python Code)

Max Activating Token Index: 845

Text #4

Max Range: 1.3958. Min Range: -1.3958

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1068329 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 1.3958. Min Range: -1.3958

Max Act: 1.2148. Min Act: -0.0000

Data Index: 159198 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1145388 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 1.3958. Min Range: -1.3958

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1440377 (Python Code)

Max Activating Token Index: 437

Text #8

Max Range: 1.3958. Min Range: -1.3958

Max Act: 1.2727. Min Act: -0.0000

Data Index: 436729 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.9773. Min Act: -0.0000

Data Index: 159230 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.9387. Min Act: -0.0000

Data Index: 807446 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.9579. Min Act: -0.0000

Data Index: 647597 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.9097. Min Act: -0.0000

Data Index: 634970 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.9591. Min Act: -0.0000

Data Index: 844565 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.9237. Min Act: -0.0000

Data Index: 12988 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.9309. Min Act: -0.0000

Data Index: 211807 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.7543. Min Act: -0.0000

Data Index: 978031 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.8925. Min Act: -0.0000

Data Index: 271922 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.8779. Min Act: -0.0000

Data Index: 941637 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 1.3958. Min Range: -1.3958

Max Act: 0.7901. Min Act: -0.0000

Data Index: 241459 (C4 (Web Text))

Max Activating Token Index: 435