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

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

Neuron 356 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: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0001

Data Index: 568657 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1129560 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1201. Min Act: -0.0001

Data Index: 921427 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1181. Min Act: -0.0002

Data Index: 158467 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1123806 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1064. Min Act: -0.0001

Data Index: 64341 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1091. Min Act: -0.0001

Data Index: 596533 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1084. Min Act: -0.0002

Data Index: 854469 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1061. Min Act: -0.0002

Data Index: 315681 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1043. Min Act: -0.0002

Data Index: 325263 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1048. Min Act: -0.0002

Data Index: 482663 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1033. Min Act: -0.0002

Data Index: 464481 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1157060 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1019. Min Act: -0.0002

Data Index: 34605 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1044. Min Act: -0.0001

Data Index: 880855 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0965. Min Act: -0.0002

Data Index: 203522 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1011. Min Act: -0.0002

Data Index: 971160 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1042. Min Act: -0.0002

Data Index: 963110 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1005. Min Act: -0.0002

Data Index: 189445 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0963. Min Act: -0.0002

Data Index: 175362 (C4 (Web Text))

Max Activating Token Index: 63