Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 683 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0004

Data Index: 1366848 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1572487 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0004

Data Index: 109214 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0004

Data Index: 214848 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0004

Data Index: 507240 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0103. Min Act: -0.0004

Data Index: 1576033 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0004

Data Index: 1596728 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0004

Data Index: 166954 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0004

Data Index: 910436 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0004

Data Index: 557030 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0004

Data Index: 1146094 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0004

Data Index: 305544 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0004

Data Index: 469687 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0107. Min Act: -0.0004

Data Index: 262935 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0098. Min Act: -0.0004

Data Index: 887171 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1416258 (Python Code)

Max Activating Token Index: 811

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1144422 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0100. Min Act: -0.0004

Data Index: 246494 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0004

Data Index: 1014805 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0091. Min Act: -0.0004

Data Index: 1537922 (Python Code)

Max Activating Token Index: 843