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

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

Neuron 1455 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.4616. Min Act: -0.0000

Data Index: 1012282 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.4118. Min Act: -0.0000

Data Index: 94053 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3848. Min Act: -0.0000

Data Index: 521157 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1165790 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2426. Min Act: -0.0000

Data Index: 862266 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.3214. Min Act: -0.0000

Data Index: 434438 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2973. Min Act: -0.0000

Data Index: 613263 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1309036 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2742. Min Act: -0.0000

Data Index: 958018 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1084934 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1191614 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2591. Min Act: -0.0000

Data Index: 493897 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2506. Min Act: -0.0000

Data Index: 133510 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2546. Min Act: -0.0000

Data Index: 756902 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2573. Min Act: -0.0000

Data Index: 319806 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2297. Min Act: 0.0001

Data Index: 892854 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.1486. Min Act: -0.0000

Data Index: 894250 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.2072. Min Act: -0.0000

Data Index: 167295 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.1366. Min Act: -0.0000

Data Index: 81172 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.1328. Min Act: 0.0001

Data Index: 1224868 (C4 (Web Text))

Max Activating Token Index: 29