Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2052 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1015237 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1249698 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2746. Min Act: -0.0000

Data Index: 676872 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2277. Min Act: -0.0000

Data Index: 889062 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2118. Min Act: -0.0000

Data Index: 372228 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2078. Min Act: -0.0000

Data Index: 975948 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2192. Min Act: -0.0000

Data Index: 2558 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2192. Min Act: -0.0000

Data Index: 518083 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2220. Min Act: -0.0000

Data Index: 682731 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2040. Min Act: -0.0000

Data Index: 299595 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2052. Min Act: -0.0000

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2055. Min Act: -0.0000

Data Index: 520488 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2046. Min Act: -0.0000

Data Index: 320908 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1942. Min Act: -0.0000

Data Index: 278401 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1935. Min Act: -0.0000

Data Index: 58532 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1751. Min Act: -0.0000

Data Index: 268471 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1927. Min Act: -0.0000

Data Index: 296627 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.2053. Min Act: -0.0000

Data Index: 634350 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1169774 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.2746. Min Range: -0.2746

Max Act: 0.1969. Min Act: -0.0000

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 543