Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5375 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4004. Min Range: -4.4004

Max Act: 4.4004. Min Act: -0.0000

Data Index: 629688 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.6518. Min Act: -0.0000

Data Index: 545753 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.8467. Min Act: -0.0000

Data Index: 1078307 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.5251. Min Act: -0.0000

Data Index: 1054260 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.3868. Min Act: -0.0000

Data Index: 273118 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.6919. Min Act: -0.0000

Data Index: 575891 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.3050. Min Act: -0.0000

Data Index: 883657 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.5404. Min Act: -0.0000

Data Index: 1287994 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.4921. Min Act: -0.0000

Data Index: 808041 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.2962. Min Act: -0.0000

Data Index: 105907 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.2864. Min Act: -0.0000

Data Index: 1231399 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.4406. Min Act: -0.0000

Data Index: 261197 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.0656. Min Act: -0.0000

Data Index: 916935 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 4.4004. Min Range: -4.4004

Max Act: 1.9414. Min Act: -0.0000

Data Index: 354813 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.2284. Min Act: -0.0000

Data Index: 1164701 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.0743. Min Act: -0.0000

Data Index: 782050 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 4.4004. Min Range: -4.4004

Max Act: 1.8098. Min Act: -0.0000

Data Index: 131489 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.1239. Min Act: -0.0000

Data Index: 188471 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.2519. Min Act: -0.0000

Data Index: 7811 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 4.4004. Min Range: -4.4004

Max Act: 2.0846. Min Act: -0.0000

Data Index: 751714 (C4 (Web Text))

Max Activating Token Index: 528