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

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

Neuron 3017 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1794. Min Range: -1.1794

Max Act: 1.1794. Min Act: -0.0000

Data Index: 708574 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9924. Min Act: -0.0000

Data Index: 289855 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9030. Min Act: -0.0000

Data Index: 26669 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.8876. Min Act: -0.0000

Data Index: 799796 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9091. Min Act: -0.0000

Data Index: 563808 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.8178. Min Act: -0.0000

Data Index: 138561 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1170951 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.9134. Min Act: -0.0000

Data Index: 848584 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1305899 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7691. Min Act: -0.0000

Data Index: 295777 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.8248. Min Act: -0.0000

Data Index: 774307 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1120805 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7954. Min Act: -0.0000

Data Index: 160750 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1214334 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7488. Min Act: -0.0000

Data Index: 234267 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.8239. Min Act: -0.0000

Data Index: 351246 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7404. Min Act: -0.0000

Data Index: 911204 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7666. Min Act: -0.0000

Data Index: 185926 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7583. Min Act: -0.0000

Data Index: 116536 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.1794. Min Range: -1.1794

Max Act: 0.7103. Min Act: -0.0000

Data Index: 242974 (C4 (Web Text))

Max Activating Token Index: 426