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

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

Neuron 5589 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: 3.3012. Min Range: -3.3012

Max Act: 3.2223. Min Act: -0.0000

Data Index: 779552 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 3.3012. Min Range: -3.3012

Max Act: 3.3012. Min Act: -0.0000

Data Index: 364260 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.6479. Min Act: -0.0000

Data Index: 772500 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.6290. Min Act: -0.0000

Data Index: 941635 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.3792. Min Act: -0.0001

Data Index: 273628 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.4222. Min Act: -0.0001

Data Index: 968259 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1881. Min Act: -0.0000

Data Index: 1082705 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1692. Min Act: -0.0000

Data Index: 375592 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.3988. Min Act: -0.0001

Data Index: 1114789 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.0858. Min Act: -0.0001

Data Index: 197520 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1903. Min Act: -0.0000

Data Index: 1290488 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.3178. Min Act: -0.0000

Data Index: 307847 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1838. Min Act: -0.0000

Data Index: 1296471 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.0801. Min Act: -0.0001

Data Index: 1201758 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1730. Min Act: -0.0000

Data Index: 355451 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.0240. Min Act: -0.0000

Data Index: 77672 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1517. Min Act: -0.0000

Data Index: 1200132 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.1082. Min Act: -0.0000

Data Index: 220101 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 3.3012. Min Range: -3.3012

Max Act: 1.9682. Min Act: -0.0000

Data Index: 956327 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 3.3012. Min Range: -3.3012

Max Act: 2.2705. Min Act: -0.0001

Data Index: 628414 (C4 (Web Text))

Max Activating Token Index: 883