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

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

Neuron 1096 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: 3.0837. Min Range: -3.0837

Max Act: 3.0232. Min Act: -0.0000

Data Index: 640944 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 3.0837. Min Range: -3.0837

Max Act: 3.0837. Min Act: -0.0000

Data Index: 230461 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 3.0837. Min Range: -3.0837

Max Act: 3.0184. Min Act: -0.0000

Data Index: 14107 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.8733. Min Act: -0.0000

Data Index: 591097 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.5729. Min Act: -0.0000

Data Index: 817912 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.5513. Min Act: -0.0001

Data Index: 405631 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.6041. Min Act: -0.0000

Data Index: 683403 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.3420. Min Act: -0.0000

Data Index: 12463 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.4453. Min Act: -0.0000

Data Index: 1061575 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.3898. Min Act: -0.0000

Data Index: 403538 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.4186. Min Act: -0.0000

Data Index: 81149 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.3563. Min Act: -0.0000

Data Index: 1048167 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.5799. Min Act: -0.0000

Data Index: 775586 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.3681. Min Act: -0.0000

Data Index: 164342 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.2402. Min Act: -0.0000

Data Index: 962841 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.3184. Min Act: -0.0000

Data Index: 956246 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.2504. Min Act: -0.0000

Data Index: 1134429 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.3641. Min Act: -0.0000

Data Index: 694670 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.2232. Min Act: -0.0000

Data Index: 721614 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 3.0837. Min Range: -3.0837

Max Act: 2.2112. Min Act: -0.0000

Data Index: 937714 (C4 (Web Text))

Max Activating Token Index: 192