Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2468 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5617. Min Act: -0.0001

Data Index: 199222 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5407. Min Act: -0.0001

Data Index: 973044 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5213. Min Act: -0.0001

Data Index: 711930 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5840. Min Act: -0.0001

Data Index: 472760 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5580. Min Act: -0.0001

Data Index: 255533 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5203. Min Act: -0.0001

Data Index: 917467 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5563. Min Act: -0.0001

Data Index: 405366 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1280118 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5182. Min Act: -0.0001

Data Index: 754253 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5210. Min Act: -0.0002

Data Index: 656530 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5097. Min Act: -0.0001

Data Index: 869921 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5060. Min Act: -0.0001

Data Index: 441367 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4878. Min Act: -0.0001

Data Index: 1169334 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5015. Min Act: -0.0001

Data Index: 791559 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4949. Min Act: -0.0001

Data Index: 1015123 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4929. Min Act: -0.0001

Data Index: 970961 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5116. Min Act: -0.0001

Data Index: 1270356 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4911. Min Act: -0.0002

Data Index: 873327 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5057. Min Act: -0.0002

Data Index: 303998 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4679. Min Act: -0.0002

Data Index: 432681 (C4 (Web Text))

Max Activating Token Index: 684