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

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

Neuron 4800 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5560. Min Act: -0.0002

Data Index: 375473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5522. Min Act: -0.0002

Data Index: 1117447 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5342. Min Act: -0.0002

Data Index: 314386 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5507. Min Act: -0.0002

Data Index: 1146562 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4907. Min Act: -0.0002

Data Index: 156652 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4791. Min Act: -0.0002

Data Index: 998196 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4705. Min Act: -0.0002

Data Index: 260796 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4845. Min Act: -0.0002

Data Index: 1200927 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5156. Min Act: -0.0002

Data Index: 148946 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4043. Min Act: -0.0002

Data Index: 812459 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4424. Min Act: -0.0002

Data Index: 223986 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4657. Min Act: -0.0002

Data Index: 640088 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4553. Min Act: -0.0002

Data Index: 578448 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4522. Min Act: -0.0002

Data Index: 1132023 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4793. Min Act: -0.0002

Data Index: 1309862 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4603. Min Act: -0.0002

Data Index: 158952 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4642. Min Act: -0.0002

Data Index: 1089503 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.5084. Min Act: -0.0002

Data Index: 1298329 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4632. Min Act: -0.0002

Data Index: 779450 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.5560. Min Range: -0.5560

Max Act: 0.4049. Min Act: -0.0002

Data Index: 229419 (C4 (Web Text))

Max Activating Token Index: 288