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

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

Neuron 2856 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: 7.1928. Min Range: -7.1928

Max Act: 6.8834. Min Act: -0.0001

Data Index: 1010734 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 7.1928. Min Range: -7.1928

Max Act: 7.1928. Min Act: -0.0001

Data Index: 516935 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 7.1928. Min Range: -7.1928

Max Act: 5.1261. Min Act: -0.0001

Data Index: 1344175 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 7.1928. Min Range: -7.1928

Max Act: 5.4719. Min Act: -0.0001

Data Index: 457481 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 7.1928. Min Range: -7.1928

Max Act: 5.2309. Min Act: -0.0001

Data Index: 98034 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.8740. Min Act: -0.0001

Data Index: 29598 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 7.1928. Min Range: -7.1928

Max Act: 5.2177. Min Act: -0.0001

Data Index: 431701 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.9437. Min Act: -0.0001

Data Index: 745265 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.7794. Min Act: -0.0000

Data Index: 171420 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.9253. Min Act: -0.0001

Data Index: 620724 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 7.1928. Min Range: -7.1928

Max Act: 5.0980. Min Act: -0.0001

Data Index: 1332452 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 7.1928. Min Range: -7.1928

Max Act: 5.2497. Min Act: -0.0001

Data Index: 679071 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.5047. Min Act: -0.0001

Data Index: 510673 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.1429. Min Act: -0.0001

Data Index: 255488 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.4536. Min Act: -0.0000

Data Index: 890562 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.9587. Min Act: -0.0001

Data Index: 746363 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.9165. Min Act: -0.0001

Data Index: 372437 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.5528. Min Act: -0.0001

Data Index: 1204719 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.2407. Min Act: -0.0000

Data Index: 629877 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 7.1928. Min Range: -7.1928

Max Act: 4.4642. Min Act: -0.0001

Data Index: 1162071 (C4 (Web Text))

Max Activating Token Index: 137