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

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

Neuron 1428 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: 2.6748. Min Range: -2.6748

Max Act: 2.6748. Min Act: -0.0000

Data Index: 626017 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.4046. Min Act: -0.0000

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.6748. Min Range: -2.6748

Max Act: 1.9286. Min Act: -0.0000

Data Index: 1107350 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0011. Min Act: -0.0000

Data Index: 1171024 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0802. Min Act: -0.0000

Data Index: 894512 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.1077. Min Act: -0.0000

Data Index: 474078 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.1066. Min Act: -0.0000

Data Index: 121444 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.1054. Min Act: -0.0000

Data Index: 438777 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0933. Min Act: -0.0000

Data Index: 1031864 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0873. Min Act: -0.0000

Data Index: 517249 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0781. Min Act: -0.0000

Data Index: 470706 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0675. Min Act: -0.0000

Data Index: 550981 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0515. Min Act: -0.0000

Data Index: 675765 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 2.6748. Min Range: -2.6748

Max Act: 1.9298. Min Act: -0.0000

Data Index: 485389 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 2.6748. Min Range: -2.6748

Max Act: 1.9111. Min Act: -0.0000

Data Index: 959989 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0137. Min Act: -0.0000

Data Index: 915019 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.1242. Min Act: -0.0000

Data Index: 295221 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 2.6748. Min Range: -2.6748

Max Act: 2.0955. Min Act: -0.0000

Data Index: 200744 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.6748. Min Range: -2.6748

Max Act: 1.9750. Min Act: -0.0000

Data Index: 524913 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 2.6748. Min Range: -2.6748

Max Act: 1.9469. Min Act: -0.0000

Data Index: 1069160 (C4 (Web Text))

Max Activating Token Index: 606