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

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

Neuron 2755 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2701. Min Act: -0.0001

Data Index: 944489 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2643. Min Act: -0.0001

Data Index: 517051 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2283. Min Act: -0.0001

Data Index: 1254954 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2277. Min Act: -0.0001

Data Index: 433716 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1163658 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2039. Min Act: -0.0001

Data Index: 366441 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2242. Min Act: -0.0001

Data Index: 971515 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2223. Min Act: -0.0001

Data Index: 955767 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1061535 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2191. Min Act: -0.0001

Data Index: 830101 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2232. Min Act: -0.0001

Data Index: 1030651 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2106. Min Act: -0.0001

Data Index: 11197 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1049216 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2163. Min Act: -0.0001

Data Index: 809472 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1271698 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2034. Min Act: -0.0001

Data Index: 364078 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2009. Min Act: -0.0001

Data Index: 795655 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.2052. Min Act: -0.0001

Data Index: 704 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1956. Min Act: -0.0001

Data Index: 719367 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.2701. Min Range: -0.2701

Max Act: 0.1830. Min Act: -0.0000

Data Index: 995836 (C4 (Web Text))

Max Activating Token Index: 108