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

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

Neuron 5370 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0002

Data Index: 210189 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0576. Min Act: -0.0002

Data Index: 382457 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0506. Min Act: -0.0002

Data Index: 665371 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0497. Min Act: -0.0002

Data Index: 407474 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1347509 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0449. Min Act: -0.0002

Data Index: 40718 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0446. Min Act: -0.0002

Data Index: 619450 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0434. Min Act: -0.0002

Data Index: 649386 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0428. Min Act: -0.0002

Data Index: 329358 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0417. Min Act: -0.0002

Data Index: 463804 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1126524 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0412. Min Act: -0.0002

Data Index: 564608 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0414. Min Act: -0.0002

Data Index: 388131 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1046088 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1202419 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0404. Min Act: -0.0002

Data Index: 720272 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1008001 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0404. Min Act: -0.0002

Data Index: 76805 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0419. Min Act: -0.0002

Data Index: 182320 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0404. Min Act: -0.0002

Data Index: 37370 (C4 (Web Text))

Max Activating Token Index: 789