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

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

Neuron 825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.2976. Min Act: -0.0000

Data Index: 669736 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.2389. Min Act: -0.0000

Data Index: 915435 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.2116. Min Act: -0.0001

Data Index: 345792 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.1904. Min Act: -0.0000

Data Index: 519089 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.2912. Min Act: -0.0001

Data Index: 669330 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.0840. Min Act: -0.0001

Data Index: 739167 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.0796. Min Act: -0.0001

Data Index: 1136146 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.0937. Min Act: -0.0000

Data Index: 638375 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.9585. Min Act: -0.0000

Data Index: 1357854 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 2.2976. Min Range: -2.2976

Max Act: 2.0560. Min Act: -0.0000

Data Index: 131301 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.8821. Min Act: -0.0000

Data Index: 1294739 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.8648. Min Act: -0.0000

Data Index: 1175290 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.8852. Min Act: -0.0000

Data Index: 966070 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.9008. Min Act: -0.0001

Data Index: 944447 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.7701. Min Act: -0.0000

Data Index: 356402 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.7832. Min Act: -0.0001

Data Index: 618201 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.7574. Min Act: -0.0001

Data Index: 899245 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.8270. Min Act: -0.0001

Data Index: 196520 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.6320. Min Act: -0.0000

Data Index: 176323 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 2.2976. Min Range: -2.2976

Max Act: 1.5760. Min Act: -0.0000

Data Index: 126027 (C4 (Web Text))

Max Activating Token Index: 367