Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 974 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1158234 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1003. Min Act: -0.0002

Data Index: 904149 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1093. Min Act: -0.0002

Data Index: 460659 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1087. Min Act: -0.0002

Data Index: 307130 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1323726 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0931. Min Act: -0.0002

Data Index: 521521 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1112. Min Act: -0.0002

Data Index: 325915 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1043. Min Act: -0.0002

Data Index: 545557 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1249354 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0923. Min Act: -0.0002

Data Index: 599331 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0945. Min Act: -0.0002

Data Index: 843388 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0929. Min Act: -0.0002

Data Index: 554016 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0926. Min Act: -0.0002

Data Index: 271530 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0979. Min Act: -0.0002

Data Index: 639994 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1280420 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0922. Min Act: -0.0002

Data Index: 172746 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0941. Min Act: -0.0002

Data Index: 128689 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1182861 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0930. Min Act: -0.0002

Data Index: 753702 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0887. Min Act: -0.0002

Data Index: 708495 (C4 (Web Text))

Max Activating Token Index: 857