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

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

Neuron 1550 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: 2.5140. Min Range: -2.5140

Max Act: 2.5140. Min Act: -0.0000

Data Index: 1133223 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 2.5140. Min Range: -2.5140

Max Act: 2.1494. Min Act: -0.0000

Data Index: 140018 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 2.5140. Min Range: -2.5140

Max Act: 2.1974. Min Act: -0.0000

Data Index: 1150341 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.8887. Min Act: -0.0000

Data Index: 502812 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.8919. Min Act: -0.0000

Data Index: 568124 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.9878. Min Act: -0.0000

Data Index: 1228434 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.8395. Min Act: -0.0000

Data Index: 894566 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.7451. Min Act: -0.0000

Data Index: 724976 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.7012. Min Act: -0.0000

Data Index: 484750 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.8756. Min Act: -0.0000

Data Index: 167557 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.6454. Min Act: -0.0000

Data Index: 34671 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.7283. Min Act: -0.0000

Data Index: 612149 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.8079. Min Act: -0.0000

Data Index: 1295824 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.9534. Min Act: -0.0000

Data Index: 49175 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.5746. Min Act: -0.0000

Data Index: 1185009 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.6499. Min Act: -0.0000

Data Index: 53045 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1324752 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.6247. Min Act: -0.0000

Data Index: 1013699 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.6251. Min Act: -0.0000

Data Index: 1264525 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 2.5140. Min Range: -2.5140

Max Act: 1.6046. Min Act: -0.0000

Data Index: 694764 (C4 (Web Text))

Max Activating Token Index: 871