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

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

Neuron 710 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1432. Min Act: -0.0001

Data Index: 410787 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1206711 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1052. Min Act: -0.0001

Data Index: 832194 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1394698 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1045913 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1027784 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1415141 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0889. Min Act: -0.0001

Data Index: 990969 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1040. Min Act: -0.0001

Data Index: 290112 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1533858 (Python Code)

Max Activating Token Index: 663

Text #10

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0887. Min Act: -0.0001

Data Index: 303123 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0938. Min Act: -0.0001

Data Index: 292440 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0938. Min Act: -0.0001

Data Index: 399944 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0877. Min Act: -0.0001

Data Index: 72496 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0878. Min Act: -0.0001

Data Index: 482820 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1287021 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1456292 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0872. Min Act: -0.0001

Data Index: 987827 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0869. Min Act: -0.0001

Data Index: 899926 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1559064 (Python Code)

Max Activating Token Index: 148