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

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

Neuron 4458 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: 2.5700. Min Range: -2.5700

Max Act: 2.5700. Min Act: -0.0000

Data Index: 1268105 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.4642. Min Act: -0.0000

Data Index: 704395 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.2536. Min Act: -0.0000

Data Index: 683767 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.3406. Min Act: -0.0000

Data Index: 303325 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.3063. Min Act: -0.0000

Data Index: 946481 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.0847. Min Act: -0.0000

Data Index: 897682 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.1120. Min Act: -0.0000

Data Index: 183879 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.1010. Min Act: -0.0000

Data Index: 474733 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.0860. Min Act: -0.0000

Data Index: 425560 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.0185. Min Act: -0.0000

Data Index: 404520 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.1125. Min Act: -0.0000

Data Index: 299180 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.1108. Min Act: -0.0000

Data Index: 1152655 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.0106. Min Act: -0.0000

Data Index: 530585 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.9969. Min Act: -0.0000

Data Index: 871946 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8916. Min Act: -0.0000

Data Index: 554276 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.0662. Min Act: -0.0000

Data Index: 997521 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 2.5700. Min Range: -2.5700

Max Act: 2.0530. Min Act: -0.0000

Data Index: 82501 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.9552. Min Act: -0.0000

Data Index: 23123 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.9249. Min Act: -0.0000

Data Index: 240664 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 2.5700. Min Range: -2.5700

Max Act: 1.8316. Min Act: -0.0000

Data Index: 491776 (C4 (Web Text))

Max Activating Token Index: 180