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

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

Neuron 4040 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.4984. Min Act: -0.0001

Data Index: 1045153 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.3012. Min Act: -0.0001

Data Index: 597344 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.4140. Min Act: -0.0001

Data Index: 451414 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.2388. Min Act: -0.0002

Data Index: 683106 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1034. Min Act: -0.0001

Data Index: 689613 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1348. Min Act: -0.0002

Data Index: 1271178 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0821. Min Act: -0.0001

Data Index: 684309 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1108. Min Act: -0.0002

Data Index: 1284525 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.1322. Min Act: -0.0002

Data Index: 331192 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0369. Min Act: -0.0002

Data Index: 798802 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0240. Min Act: -0.0001

Data Index: 325833 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0164. Min Act: -0.0002

Data Index: 312676 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0095. Min Act: -0.0002

Data Index: 742 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0236. Min Act: -0.0002

Data Index: 1233162 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0262. Min Act: -0.0001

Data Index: 598231 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 1.4984. Min Range: -1.4984

Max Act: 0.9744. Min Act: -0.0002

Data Index: 437751 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0023. Min Act: -0.0002

Data Index: 47391 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.4984. Min Range: -1.4984

Max Act: 0.9727. Min Act: -0.0001

Data Index: 535711 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0174. Min Act: -0.0001

Data Index: 809964 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 1.4984. Min Range: -1.4984

Max Act: 1.0097. Min Act: -0.0001

Data Index: 654202 (C4 (Web Text))

Max Activating Token Index: 770