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

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

Neuron 3566 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1248. Min Act: -0.0002

Data Index: 684736 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1311207 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1174. Min Act: -0.0001

Data Index: 850732 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1281358 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1125372 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1020. Min Act: -0.0001

Data Index: 759005 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1007. Min Act: -0.0001

Data Index: 504516 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0974. Min Act: -0.0001

Data Index: 909753 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1559175 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0951. Min Act: -0.0002

Data Index: 9117 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0994. Min Act: -0.0001

Data Index: 573250 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1020. Min Act: -0.0001

Data Index: 238452 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0953. Min Act: -0.0001

Data Index: 714497 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1071381 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0872. Min Act: -0.0001

Data Index: 761191 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0992. Min Act: -0.0001

Data Index: 47712 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0899. Min Act: -0.0001

Data Index: 59296 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0925. Min Act: -0.0001

Data Index: 258418 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1173217 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0942. Min Act: -0.0002

Data Index: 454600 (C4 (Web Text))

Max Activating Token Index: 307