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

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

Neuron 1800 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: 0.1254. Min Range: -0.1254

Max Act: 0.1254. Min Act: -0.0002

Data Index: 1004938 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1226. Min Act: -0.0002

Data Index: 91565 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1337781 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1162. Min Act: -0.0002

Data Index: 850654 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1216. Min Act: -0.0002

Data Index: 779223 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1069. Min Act: -0.0002

Data Index: 553096 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1108078 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1112. Min Act: -0.0002

Data Index: 60709 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1110. Min Act: -0.0002

Data Index: 859795 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1110. Min Act: -0.0002

Data Index: 748872 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1061. Min Act: -0.0002

Data Index: 842607 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1096. Min Act: -0.0002

Data Index: 401025 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1063. Min Act: -0.0002

Data Index: 466836 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1084. Min Act: -0.0002

Data Index: 63680 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1214051 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1094. Min Act: -0.0002

Data Index: 899530 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1076. Min Act: -0.0002

Data Index: 995697 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1056. Min Act: -0.0002

Data Index: 861769 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1028. Min Act: -0.0002

Data Index: 214113 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1028. Min Act: -0.0002

Data Index: 222913 (C4 (Web Text))

Max Activating Token Index: 40