Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 478 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0128. Min Act: -0.0002

Data Index: 310950 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0126. Min Act: -0.0002

Data Index: 716438 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0124. Min Act: -0.0002

Data Index: 756775 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1061270 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0117. Min Act: -0.0002

Data Index: 3222 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0116. Min Act: -0.0002

Data Index: 836073 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0116. Min Act: -0.0002

Data Index: 281980 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0116. Min Act: -0.0002

Data Index: 587025 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1623969 (Python Code)

Max Activating Token Index: 226

Text #9

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1466472 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0114. Min Act: -0.0002

Data Index: 378612 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1351628 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1008057 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0113. Min Act: -0.0002

Data Index: 126460 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0113. Min Act: -0.0002

Data Index: 881343 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1250247 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1027876 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0112. Min Act: -0.0002

Data Index: 935292 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0112. Min Act: -0.0002

Data Index: 226403 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1105472 (C4 (Web Text))

Max Activating Token Index: 700