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

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

Neuron 615 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: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0005

Data Index: 898252 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0179. Min Act: -0.0005

Data Index: 883170 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0110. Min Act: -0.0005

Data Index: 173131 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0107. Min Act: -0.0005

Data Index: 1339169 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0105. Min Act: -0.0005

Data Index: 624726 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0106. Min Act: -0.0005

Data Index: 915830 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0108. Min Act: -0.0005

Data Index: 97663 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0105. Min Act: -0.0005

Data Index: 1236492 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0101. Min Act: -0.0005

Data Index: 1156576 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0103. Min Act: -0.0005

Data Index: 149464 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0103. Min Act: -0.0005

Data Index: 1014846 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0101. Min Act: -0.0005

Data Index: 705485 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0102. Min Act: -0.0005

Data Index: 418302 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0098. Min Act: -0.0005

Data Index: 992084 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0101. Min Act: -0.0005

Data Index: 1540158 (Python Code)

Max Activating Token Index: 773

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0102. Min Act: -0.0005

Data Index: 694777 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0102. Min Act: -0.0005

Data Index: 985586 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0100. Min Act: -0.0005

Data Index: 913944 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0102. Min Act: -0.0005

Data Index: 563243 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0100. Min Act: -0.0005

Data Index: 850104 (C4 (Web Text))

Max Activating Token Index: 734