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

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

Neuron 3980 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: 5.3832. Min Range: -5.3832

Max Act: 5.3832. Min Act: -0.0000

Data Index: 778152 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 5.3832. Min Range: -5.3832

Max Act: 4.6743. Min Act: -0.0001

Data Index: 1213205 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 5.3832. Min Range: -5.3832

Max Act: 4.0383. Min Act: -0.0000

Data Index: 1177289 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.4065. Min Act: -0.0000

Data Index: 376664 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.5349. Min Act: -0.0001

Data Index: 537867 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.3245. Min Act: -0.0000

Data Index: 714783 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.2116. Min Act: -0.0001

Data Index: 921744 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.1644. Min Act: -0.0000

Data Index: 1012575 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.1042. Min Act: -0.0000

Data Index: 354335 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.0816. Min Act: -0.0000

Data Index: 1320790 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.0561. Min Act: -0.0000

Data Index: 268753 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.1643. Min Act: -0.0001

Data Index: 104259 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.2223. Min Act: -0.0000

Data Index: 488283 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 5.3832. Min Range: -5.3832

Max Act: 3.0193. Min Act: -0.0000

Data Index: 601451 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 5.3832. Min Range: -5.3832

Max Act: 2.7330. Min Act: -0.0001

Data Index: 253090 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 5.3832. Min Range: -5.3832

Max Act: 2.8418. Min Act: -0.0001

Data Index: 951103 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 5.3832. Min Range: -5.3832

Max Act: 2.9076. Min Act: -0.0000

Data Index: 578649 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 5.3832. Min Range: -5.3832

Max Act: 2.6131. Min Act: -0.0000

Data Index: 177995 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 5.3832. Min Range: -5.3832

Max Act: 2.7209. Min Act: -0.0000

Data Index: 596288 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 5.3832. Min Range: -5.3832

Max Act: 2.7020. Min Act: -0.0001

Data Index: 873009 (C4 (Web Text))

Max Activating Token Index: 377