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

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

Neuron 1177 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1084. Min Act: -0.0001

Data Index: 376331 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1096886 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1151. Min Act: -0.0001

Data Index: 948236 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1271355 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1208. Min Act: -0.0001

Data Index: 796390 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1045. Min Act: -0.0001

Data Index: 330938 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0983. Min Act: -0.0001

Data Index: 200667 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1106191 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1273432 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1287842 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1247038 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0951. Min Act: -0.0001

Data Index: 705136 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0945. Min Act: -0.0001

Data Index: 736916 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0994. Min Act: -0.0001

Data Index: 491764 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0946. Min Act: -0.0001

Data Index: 369531 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1573214 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0933. Min Act: -0.0001

Data Index: 582962 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0919. Min Act: -0.0001

Data Index: 569834 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0955. Min Act: -0.0001

Data Index: 483948 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.1208. Min Range: -0.1208

Max Act: 0.0921. Min Act: -0.0001

Data Index: 107299 (C4 (Web Text))

Max Activating Token Index: 378