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

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

Neuron 3003 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: 4.2852. Min Range: -4.2852

Max Act: 4.2852. Min Act: -0.0000

Data Index: 550397 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 4.2852. Min Range: -4.2852

Max Act: 3.7841. Min Act: -0.0000

Data Index: 357137 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 4.2852. Min Range: -4.2852

Max Act: 3.3011. Min Act: -0.0000

Data Index: 1219555 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 4.2852. Min Range: -4.2852

Max Act: 3.2375. Min Act: -0.0000

Data Index: 875129 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 4.2852. Min Range: -4.2852

Max Act: 3.0579. Min Act: -0.0000

Data Index: 681547 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 4.2852. Min Range: -4.2852

Max Act: 3.0045. Min Act: -0.0000

Data Index: 967622 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.9703. Min Act: -0.0000

Data Index: 1010268 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.9935. Min Act: -0.0000

Data Index: 762607 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.5518. Min Act: -0.0000

Data Index: 1169322 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.6885. Min Act: -0.0000

Data Index: 1191089 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.7833. Min Act: -0.0000

Data Index: 97386 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.6252. Min Act: -0.0000

Data Index: 913944 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.7530. Min Act: -0.0000

Data Index: 1085131 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.4690. Min Act: -0.0000

Data Index: 186423 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.3124. Min Act: -0.0000

Data Index: 441556 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.5170. Min Act: -0.0000

Data Index: 930068 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.5095. Min Act: -0.0000

Data Index: 573705 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.5182. Min Act: -0.0000

Data Index: 45860 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.4851. Min Act: -0.0000

Data Index: 517249 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 4.2852. Min Range: -4.2852

Max Act: 2.5586. Min Act: -0.0000

Data Index: 110754 (C4 (Web Text))

Max Activating Token Index: 500