Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1999 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1164386 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0098. Min Act: -0.0006

Data Index: 145132 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0096. Min Act: -0.0006

Data Index: 200876 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0095. Min Act: -0.0006

Data Index: 177047 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1029714 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0092. Min Act: -0.0006

Data Index: 716412 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1335370 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0091. Min Act: -0.0006

Data Index: 642183 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0092. Min Act: -0.0006

Data Index: 612881 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0090. Min Act: -0.0006

Data Index: 833794 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1123617 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0088. Min Act: -0.0006

Data Index: 526428 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0086. Min Act: -0.0006

Data Index: 339872 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0087. Min Act: -0.0006

Data Index: 409791 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1355657 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1017282 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0083. Min Act: -0.0006

Data Index: 705649 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0084. Min Act: -0.0006

Data Index: 437010 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1066176 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1238507 (C4 (Web Text))

Max Activating Token Index: 329