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

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

Neuron 4070 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.6796. Min Act: -0.0000

Data Index: 406354 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5103. Min Act: -0.0000

Data Index: 98638 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5691. Min Act: -0.0000

Data Index: 968625 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1113148 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5544. Min Act: -0.0000

Data Index: 781426 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1111109 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4877. Min Act: -0.0000

Data Index: 724746 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1072104 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4984. Min Act: -0.0000

Data Index: 368283 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5044. Min Act: -0.0000

Data Index: 962422 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4906. Min Act: -0.0000

Data Index: 269191 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4824. Min Act: -0.0000

Data Index: 158690 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4866. Min Act: -0.0000

Data Index: 666660 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4797. Min Act: -0.0000

Data Index: 150952 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4899. Min Act: -0.0001

Data Index: 427662 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4734. Min Act: -0.0000

Data Index: 481743 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.5352. Min Act: -0.0000

Data Index: 130900 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4558. Min Act: -0.0000

Data Index: 214307 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4406. Min Act: -0.0000

Data Index: 208953 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.6796. Min Range: -0.6796

Max Act: 0.4607. Min Act: -0.0000

Data Index: 54151 (C4 (Web Text))

Max Activating Token Index: 451