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

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

Neuron 5445 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6386. Min Act: -0.0000

Data Index: 119735 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.6752. Min Act: -0.0000

Data Index: 298854 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5945. Min Act: 0.0000

Data Index: 1079624 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1052451 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5733. Min Act: -0.0000

Data Index: 101656 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5359. Min Act: -0.0000

Data Index: 791747 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5083. Min Act: -0.0000

Data Index: 952393 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1093640 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1107386 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4920. Min Act: -0.0000

Data Index: 258384 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1069602 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4904. Min Act: -0.0000

Data Index: 99190 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4666. Min Act: -0.0000

Data Index: 993075 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4621. Min Act: -0.0000

Data Index: 160301 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4772. Min Act: -0.0000

Data Index: 530054 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4526. Min Act: -0.0000

Data Index: 626320 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4590. Min Act: -0.0000

Data Index: 632806 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4376. Min Act: -0.0000

Data Index: 907329 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4271. Min Act: -0.0000

Data Index: 600004 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.6752. Min Range: -0.6752

Max Act: 0.4046. Min Act: -0.0000

Data Index: 273271 (C4 (Web Text))

Max Activating Token Index: 801