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

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

Neuron 534 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: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0005

Data Index: 36093 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0089. Min Act: -0.0005

Data Index: 498338 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0005

Data Index: 950553 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0006

Data Index: 918542 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1155187 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0087. Min Act: -0.0005

Data Index: 120375 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0085. Min Act: -0.0005

Data Index: 987801 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0084. Min Act: -0.0005

Data Index: 1283525 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0005

Data Index: 612217 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0082. Min Act: -0.0005

Data Index: 818908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1298515 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0080. Min Act: -0.0005

Data Index: 446530 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0005

Data Index: 58839 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0079. Min Act: -0.0005

Data Index: 1312020 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0005

Data Index: 395520 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0079. Min Act: -0.0005

Data Index: 171959 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1202726 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0079. Min Act: -0.0005

Data Index: 1210303 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0078. Min Act: -0.0005

Data Index: 201278 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0077. Min Act: -0.0005

Data Index: 1113903 (C4 (Web Text))

Max Activating Token Index: 89