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

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

Neuron 124 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: 0.0095. Min Range: -0.0095

Max Act: 0.0095. Min Act: -0.0005

Data Index: 461470 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0094. Min Act: -0.0005

Data Index: 925752 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0094. Min Act: -0.0005

Data Index: 549979 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0091. Min Act: -0.0005

Data Index: 1329732 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0087. Min Act: -0.0005

Data Index: 571178 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0092. Min Act: -0.0005

Data Index: 540234 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0083. Min Act: -0.0005

Data Index: 522794 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0005

Data Index: 322315 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0087. Min Act: -0.0005

Data Index: 841535 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0085. Min Act: -0.0005

Data Index: 37154 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1002981 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0087. Min Act: -0.0005

Data Index: 464594 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0084. Min Act: -0.0005

Data Index: 362493 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0089. Min Act: -0.0005

Data Index: 1157442 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0085. Min Act: -0.0005

Data Index: 471521 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0005

Data Index: 96751 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0085. Min Act: -0.0005

Data Index: 229256 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1319868 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1181283 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0086. Min Act: -0.0005

Data Index: 932186 (C4 (Web Text))

Max Activating Token Index: 216