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

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

Neuron 1590 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: 1.2518. Min Range: -1.2518

Max Act: 1.2518. Min Act: -0.0002

Data Index: 30947 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.1185. Min Act: -0.0002

Data Index: 1141526 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.1359. Min Act: -0.0002

Data Index: 309108 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.1148. Min Act: -0.0002

Data Index: 256807 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0931. Min Act: -0.0002

Data Index: 269061 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0916. Min Act: -0.0002

Data Index: 1393379 (Python Code)

Max Activating Token Index: 702

Text #6

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0773. Min Act: -0.0002

Data Index: 826636 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.1041. Min Act: -0.0002

Data Index: 954746 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0485. Min Act: -0.0002

Data Index: 1174225 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0557. Min Act: -0.0002

Data Index: 499001 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0637. Min Act: -0.0002

Data Index: 688986 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0593. Min Act: -0.0002

Data Index: 1033721 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0734. Min Act: -0.0002

Data Index: 440393 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0512. Min Act: -0.0002

Data Index: 624825 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0601. Min Act: -0.0002

Data Index: 1219629 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0797. Min Act: -0.0002

Data Index: 659269 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0754. Min Act: -0.0002

Data Index: 990593 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0410. Min Act: -0.0002

Data Index: 645323 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0319. Min Act: -0.0002

Data Index: 400350 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.2518. Min Range: -1.2518

Max Act: 1.0392. Min Act: -0.0002

Data Index: 1103608 (C4 (Web Text))

Max Activating Token Index: 675