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

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

Neuron 1447 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 4.1848. Min Range: -4.1848

Max Act: 4.0919. Min Act: -0.0002

Data Index: 66300 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 4.1848. Min Range: -4.1848

Max Act: 4.1848. Min Act: -0.0002

Data Index: 53563 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 4.1848. Min Range: -4.1848

Max Act: 4.0983. Min Act: -0.0002

Data Index: 1259011 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.9993. Min Act: -0.0002

Data Index: 501157 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 4.1848. Min Range: -4.1848

Max Act: 4.0687. Min Act: -0.0002

Data Index: 192484 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 4.1848. Min Range: -4.1848

Max Act: 4.1364. Min Act: -0.0002

Data Index: 959947 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.9873. Min Act: -0.0002

Data Index: 814973 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 4.1848. Min Range: -4.1848

Max Act: 4.0076. Min Act: -0.0002

Data Index: 244809 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.9462. Min Act: -0.0002

Data Index: 519363 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.8892. Min Act: -0.0002

Data Index: 453510 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.9424. Min Act: -0.0002

Data Index: 818701 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.7634. Min Act: -0.0002

Data Index: 179782 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.7502. Min Act: -0.0002

Data Index: 756640 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.7579. Min Act: -0.0002

Data Index: 119678 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.8135. Min Act: -0.0002

Data Index: 740594 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.7164. Min Act: -0.0002

Data Index: 513968 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.7491. Min Act: -0.0002

Data Index: 1140045 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.7838. Min Act: -0.0002

Data Index: 1243004 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.6367. Min Act: -0.0002

Data Index: 1213887 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 4.1848. Min Range: -4.1848

Max Act: 3.6841. Min Act: -0.0002

Data Index: 808282 (C4 (Web Text))

Max Activating Token Index: 115