Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1302 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1985. Min Act: -0.0000

Data Index: 357962 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1214. Min Act: -0.0000

Data Index: 381509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1135. Min Act: -0.0000

Data Index: 984524 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1495488 (Python Code)

Max Activating Token Index: 918

Text #4

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1163766 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0893. Min Act: -0.0000

Data Index: 873904 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1288225 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1049284 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1047. Min Act: -0.0000

Data Index: 15004 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0900. Min Act: -0.0000

Data Index: 197174 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0778. Min Act: -0.0000

Data Index: 539899 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1091. Min Act: -0.0000

Data Index: 749835 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0855. Min Act: -0.0000

Data Index: 623877 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0720. Min Act: -0.0000

Data Index: 633384 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0856. Min Act: -0.0000

Data Index: 804391 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0939. Min Act: -0.0000

Data Index: 831180 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0776. Min Act: -0.0000

Data Index: 503130 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0910. Min Act: -0.0000

Data Index: 486335 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0725. Min Act: -0.0000

Data Index: 684229 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.0943. Min Act: -0.0000

Data Index: 331591 (C4 (Web Text))

Max Activating Token Index: 357