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

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

Neuron 3767 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3701. Min Range: -3.3701

Max Act: 3.3701. Min Act: -0.0000

Data Index: 136850 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 3.3701. Min Range: -3.3701

Max Act: 2.9062. Min Act: -0.0000

Data Index: 672446 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 3.3701. Min Range: -3.3701

Max Act: 2.6884. Min Act: -0.0000

Data Index: 1062267 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 3.3701. Min Range: -3.3701

Max Act: 2.4054. Min Act: -0.0000

Data Index: 1033300 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 3.3701. Min Range: -3.3701

Max Act: 2.4244. Min Act: -0.0000

Data Index: 620963 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 3.3701. Min Range: -3.3701

Max Act: 2.1691. Min Act: -0.0000

Data Index: 1324921 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.3701. Min Range: -3.3701

Max Act: 2.1161. Min Act: -0.0000

Data Index: 1068663 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 3.3701. Min Range: -3.3701

Max Act: 2.1142. Min Act: -0.0000

Data Index: 289102 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.7183. Min Act: -0.0000

Data Index: 1224672 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.9228. Min Act: -0.0000

Data Index: 299894 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.8174. Min Act: -0.0000

Data Index: 80151 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.9189. Min Act: -0.0000

Data Index: 761628 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.7880. Min Act: -0.0000

Data Index: 999881 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.8791. Min Act: -0.0000

Data Index: 182389 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.8671. Min Act: -0.0000

Data Index: 598187 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.7545. Min Act: -0.0000

Data Index: 1135577 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.7501. Min Act: -0.0000

Data Index: 1024783 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.7231. Min Act: -0.0000

Data Index: 771790 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.7127. Min Act: -0.0000

Data Index: 614281 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 3.3701. Min Range: -3.3701

Max Act: 1.6978. Min Act: -0.0000

Data Index: 1249663 (C4 (Web Text))

Max Activating Token Index: 394