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

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

Neuron 3923 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: 5.0497. Min Range: -5.0497

Max Act: 5.0497. Min Act: -0.0000

Data Index: 459805 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.3279. Min Act: -0.0000

Data Index: 1125052 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.4520. Min Act: -0.0000

Data Index: 778547 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.4505. Min Act: -0.0000

Data Index: 676500 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.2817. Min Act: -0.0000

Data Index: 648244 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.2622. Min Act: -0.0000

Data Index: 1148515 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.4156. Min Act: -0.0000

Data Index: 251942 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.2394. Min Act: -0.0000

Data Index: 591170 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.2344. Min Act: -0.0000

Data Index: 1265038 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.0229. Min Act: -0.0000

Data Index: 250188 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.0073. Min Act: -0.0000

Data Index: 1104762 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.1754. Min Act: -0.0000

Data Index: 854937 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 5.0497. Min Range: -5.0497

Max Act: 3.9760. Min Act: -0.0000

Data Index: 27347 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 5.0497. Min Range: -5.0497

Max Act: 3.8981. Min Act: -0.0000

Data Index: 957376 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 5.0497. Min Range: -5.0497

Max Act: 3.9022. Min Act: -0.0000

Data Index: 698736 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.0559. Min Act: -0.0000

Data Index: 373718 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 5.0497. Min Range: -5.0497

Max Act: 4.0271. Min Act: -0.0000

Data Index: 362004 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 5.0497. Min Range: -5.0497

Max Act: 3.8511. Min Act: -0.0000

Data Index: 519183 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 5.0497. Min Range: -5.0497

Max Act: 3.9804. Min Act: -0.0000

Data Index: 849455 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 5.0497. Min Range: -5.0497

Max Act: 3.8311. Min Act: -0.0000

Data Index: 98582 (C4 (Web Text))

Max Activating Token Index: 877