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

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

Neuron 4620 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.5687. Min Act: -0.0001

Data Index: 967072 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.6699. Min Act: -0.0001

Data Index: 844275 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.5985. Min Act: -0.0001

Data Index: 1062504 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.6103. Min Act: -0.0001

Data Index: 685694 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.8063. Min Act: -0.0001

Data Index: 157355 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4129. Min Act: -0.0001

Data Index: 1182682 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.5070. Min Act: -0.0001

Data Index: 190450 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4619. Min Act: -0.0001

Data Index: 978266 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4639. Min Act: -0.0001

Data Index: 1215028 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4438. Min Act: -0.0001

Data Index: 432687 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3693. Min Act: -0.0001

Data Index: 110413 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3118. Min Act: -0.0001

Data Index: 688526 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3760. Min Act: -0.0001

Data Index: 194856 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3834. Min Act: -0.0001

Data Index: 1350526 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.4131. Min Act: -0.0001

Data Index: 1058371 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3386. Min Act: -0.0001

Data Index: 312840 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.2588. Min Act: -0.0001

Data Index: 49469 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.1690. Min Act: -0.0001

Data Index: 1331373 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.2585. Min Act: -0.0001

Data Index: 1178268 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.8063. Min Range: -1.8063

Max Act: 1.3809. Min Act: -0.0001

Data Index: 1010755 (C4 (Web Text))

Max Activating Token Index: 361