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

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

Neuron 21 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4245. Min Range: -5.4245

Max Act: 5.4245. Min Act: -0.0000

Data Index: 961125 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 5.4245. Min Range: -5.4245

Max Act: 5.3916. Min Act: -0.0000

Data Index: 971984 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 5.4245. Min Range: -5.4245

Max Act: 4.5685. Min Act: -0.0000

Data Index: 1199958 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 5.4245. Min Range: -5.4245

Max Act: 4.6567. Min Act: -0.0000

Data Index: 34159 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 5.4245. Min Range: -5.4245

Max Act: 4.0620. Min Act: -0.0000

Data Index: 998556 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.9320. Min Act: -0.0000

Data Index: 864906 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 5.4245. Min Range: -5.4245

Max Act: 4.3974. Min Act: -0.0001

Data Index: 548999 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.9794. Min Act: -0.0000

Data Index: 364127 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 5.4245. Min Range: -5.4245

Max Act: 4.1085. Min Act: -0.0001

Data Index: 757156 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.6531. Min Act: -0.0001

Data Index: 26374 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.6510. Min Act: -0.0000

Data Index: 232297 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.4728. Min Act: -0.0000

Data Index: 7918 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.4793. Min Act: -0.0001

Data Index: 228110 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.6248. Min Act: -0.0001

Data Index: 478816 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.5751. Min Act: -0.0000

Data Index: 1269190 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.5621. Min Act: -0.0001

Data Index: 1224153 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.4493. Min Act: -0.0001

Data Index: 162664 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.7518. Min Act: -0.0000

Data Index: 1076874 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.4969. Min Act: -0.0001

Data Index: 690732 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 5.4245. Min Range: -5.4245

Max Act: 3.2448. Min Act: -0.0001

Data Index: 1314340 (C4 (Web Text))

Max Activating Token Index: 1008