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

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

Neuron 888 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: 0.1293. Min Range: -0.1293

Max Act: 0.1293. Min Act: -0.0002

Data Index: 432021 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1139. Min Act: -0.0002

Data Index: 701360 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1130. Min Act: -0.0002

Data Index: 525804 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1096. Min Act: -0.0002

Data Index: 740694 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1050. Min Act: -0.0002

Data Index: 293865 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1033. Min Act: -0.0002

Data Index: 331834 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1097602 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1354435 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1017. Min Act: -0.0002

Data Index: 713268 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0990. Min Act: -0.0002

Data Index: 755017 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0975. Min Act: -0.0002

Data Index: 609354 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0944. Min Act: -0.0002

Data Index: 816345 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0985. Min Act: -0.0002

Data Index: 162954 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1345088 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1148209 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0972. Min Act: -0.0002

Data Index: 182844 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1277096 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1176571 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1233176 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0917. Min Act: -0.0002

Data Index: 284165 (C4 (Web Text))

Max Activating Token Index: 901