Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2976 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.2701. Min Range: -6.2701

Max Act: 6.2701. Min Act: -0.0000

Data Index: 425863 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 6.2701. Min Range: -6.2701

Max Act: 6.2424. Min Act: -0.0000

Data Index: 1321794 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 6.2701. Min Range: -6.2701

Max Act: 6.1209. Min Act: -0.0000

Data Index: 1292464 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 6.2701. Min Range: -6.2701

Max Act: 5.9145. Min Act: -0.0000

Data Index: 540284 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 6.2701. Min Range: -6.2701

Max Act: 5.5583. Min Act: -0.0000

Data Index: 420820 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 6.2701. Min Range: -6.2701

Max Act: 5.1102. Min Act: -0.0000

Data Index: 38448 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 6.2701. Min Range: -6.2701

Max Act: 5.1052. Min Act: -0.0000

Data Index: 1067964 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 6.2701. Min Range: -6.2701

Max Act: 4.2603. Min Act: -0.0000

Data Index: 469627 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.9278. Min Act: -0.0000

Data Index: 269513 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 6.2701. Min Range: -6.2701

Max Act: 4.1826. Min Act: -0.0000

Data Index: 988974 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.9488. Min Act: -0.0000

Data Index: 186097 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 6.2701. Min Range: -6.2701

Max Act: 4.0662. Min Act: -0.0000

Data Index: 561696 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 6.2701. Min Range: -6.2701

Max Act: 4.0438. Min Act: -0.0000

Data Index: 265580 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.6227. Min Act: -0.0000

Data Index: 541810 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.5964. Min Act: -0.0000

Data Index: 748334 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.7238. Min Act: -0.0000

Data Index: 908759 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.4630. Min Act: -0.0000

Data Index: 987842 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.3325. Min Act: -0.0000

Data Index: 885542 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.0238. Min Act: -0.0000

Data Index: 471919 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 6.2701. Min Range: -6.2701

Max Act: 3.1481. Min Act: -0.0000

Data Index: 464003 (C4 (Web Text))

Max Activating Token Index: 800