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

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

Neuron 5866 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1591. Min Act: -0.0001

Data Index: 845679 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1430. Min Act: -0.0001

Data Index: 19888 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1471. Min Act: -0.0001

Data Index: 447410 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1340. Min Act: -0.0001

Data Index: 148957 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1294. Min Act: -0.0002

Data Index: 442861 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1340959 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1212. Min Act: -0.0001

Data Index: 748071 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1195. Min Act: -0.0001

Data Index: 925710 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1177. Min Act: -0.0001

Data Index: 835761 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1095. Min Act: -0.0001

Data Index: 176072 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1195. Min Act: -0.0001

Data Index: 334795 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1279. Min Act: -0.0001

Data Index: 998439 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1116. Min Act: -0.0001

Data Index: 42992 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1262. Min Act: -0.0001

Data Index: 504240 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1094. Min Act: -0.0001

Data Index: 423910 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1090. Min Act: -0.0001

Data Index: 166728 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1203. Min Act: -0.0001

Data Index: 993138 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1089. Min Act: -0.0001

Data Index: 711568 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1113. Min Act: -0.0001

Data Index: 52457 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1145. Min Act: -0.0001

Data Index: 150729 (C4 (Web Text))

Max Activating Token Index: 214