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

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

Neuron 2636 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: 0.6968. Min Range: -0.6968

Max Act: 0.6937. Min Act: -0.0002

Data Index: 1343280 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6968. Min Act: -0.0002

Data Index: 205832 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6676. Min Act: -0.0002

Data Index: 778534 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6567. Min Act: -0.0002

Data Index: 768479 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6545. Min Act: -0.0002

Data Index: 897353 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6570. Min Act: -0.0002

Data Index: 1195248 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6634. Min Act: -0.0002

Data Index: 1052571 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6596. Min Act: -0.0002

Data Index: 62815 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6470. Min Act: -0.0002

Data Index: 825881 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6428. Min Act: -0.0002

Data Index: 162204 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6509. Min Act: -0.0002

Data Index: 998715 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6497. Min Act: -0.0002

Data Index: 566598 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6476. Min Act: -0.0002

Data Index: 283985 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6429. Min Act: -0.0002

Data Index: 1174305 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6586. Min Act: -0.0002

Data Index: 461821 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6462. Min Act: -0.0002

Data Index: 130703 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6414. Min Act: -0.0002

Data Index: 1303979 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6386. Min Act: -0.0002

Data Index: 683736 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6253. Min Act: -0.0002

Data Index: 626931 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6295. Min Act: -0.0002

Data Index: 1269594 (C4 (Web Text))

Max Activating Token Index: 220