Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 649 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1650346 (Python Code)

Max Activating Token Index: 501

Text #1

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0086. Min Act: -0.0005

Data Index: 320362 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1594001 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1559074 (Python Code)

Max Activating Token Index: 522

Text #4

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0082. Min Act: -0.0005

Data Index: 432221 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0080. Min Act: -0.0005

Data Index: 1509891 (Python Code)

Max Activating Token Index: 506

Text #6

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0079. Min Act: -0.0004

Data Index: 1365422 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1530026 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0076. Min Act: -0.0005

Data Index: 1159940 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0076. Min Act: -0.0005

Data Index: 137103 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0075. Min Act: -0.0005

Data Index: 1168020 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0076. Min Act: -0.0004

Data Index: 1640467 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1645167 (Python Code)

Max Activating Token Index: 496

Text #13

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0075. Min Act: -0.0005

Data Index: 1354935 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0073. Min Act: -0.0005

Data Index: 1289007 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1493137 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0073. Min Act: -0.0004

Data Index: 1373157 (Python Code)

Max Activating Token Index: 532

Text #17

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0072. Min Act: -0.0006

Data Index: 261095 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1596222 (Python Code)

Max Activating Token Index: 548

Text #19

Max Range: 0.0109. Min Range: -0.0109

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1533040 (Python Code)

Max Activating Token Index: 476