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

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

Neuron 1004 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: 2.0886. Min Range: -2.0886

Max Act: 2.0886. Min Act: -0.0000

Data Index: 162127 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.4252. Min Act: -0.0000

Data Index: 411417 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.3791. Min Act: -0.0000

Data Index: 876397 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.3703. Min Act: -0.0000

Data Index: 308856 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1225458 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1021335 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1678. Min Act: -0.0000

Data Index: 975385 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1832. Min Act: -0.0000

Data Index: 281375 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.2018. Min Act: -0.0000

Data Index: 854221 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1946. Min Act: -0.0000

Data Index: 966369 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1132. Min Act: -0.0000

Data Index: 836867 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1773. Min Act: -0.0000

Data Index: 809191 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1066512 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1668. Min Act: -0.0000

Data Index: 933174 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1096. Min Act: -0.0000

Data Index: 995999 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1223. Min Act: -0.0000

Data Index: 574139 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1129. Min Act: -0.0000

Data Index: 498494 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.1054. Min Act: -0.0000

Data Index: 520699 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.0632. Min Act: -0.0000

Data Index: 723608 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 2.0886. Min Range: -2.0886

Max Act: 1.0171. Min Act: -0.0000

Data Index: 722586 (C4 (Web Text))

Max Activating Token Index: 502