Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3120 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1277811 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1143. Min Act: -0.0000

Data Index: 799709 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1150162 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1175. Min Act: -0.0000

Data Index: 951554 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1563402 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1061. Min Act: -0.0000

Data Index: 747364 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1013. Min Act: -0.0001

Data Index: 312941 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0901. Min Act: -0.0000

Data Index: 86057 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0939. Min Act: -0.0000

Data Index: 158506 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0929. Min Act: -0.0001

Data Index: 827446 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1005. Min Act: -0.0000

Data Index: 684543 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0779. Min Act: -0.0000

Data Index: 895578 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0879. Min Act: -0.0001

Data Index: 184925 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0884. Min Act: -0.0001

Data Index: 175131 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1405125 (Python Code)

Max Activating Token Index: 406

Text #15

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0849. Min Act: -0.0000

Data Index: 645925 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1009151 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1242033 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0826. Min Act: -0.0001

Data Index: 662548 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0836. Min Act: -0.0000

Data Index: 405795 (C4 (Web Text))

Max Activating Token Index: 360