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

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

Neuron 2739 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1053053 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: 0.0001

Data Index: 1288482 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1186. Min Act: -0.0001

Data Index: 185537 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1315090 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1215707 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1189022 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1061. Min Act: -0.0001

Data Index: 258822 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1084. Min Act: -0.0000

Data Index: 767162 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1047. Min Act: -0.0001

Data Index: 900531 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1055. Min Act: -0.0001

Data Index: 64660 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1081. Min Act: -0.0001

Data Index: 166192 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1024. Min Act: -0.0001

Data Index: 944568 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1049. Min Act: -0.0001

Data Index: 979723 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0985. Min Act: -0.0001

Data Index: 864821 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0939. Min Act: -0.0001

Data Index: 43376 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1225306 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0959. Min Act: -0.0001

Data Index: 4805 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0961. Min Act: -0.0000

Data Index: 607426 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0996. Min Act: -0.0001

Data Index: 875409 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0988. Min Act: -0.0001

Data Index: 79710 (C4 (Web Text))

Max Activating Token Index: 166