Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 494 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1489. Min Act: -0.0003

Data Index: 65839 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1595. Min Act: -0.0003

Data Index: 495218 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1616. Min Act: -0.0003

Data Index: 588744 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1501. Min Act: -0.0003

Data Index: 2512 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1479. Min Act: -0.0003

Data Index: 447218 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1579. Min Act: -0.0003

Data Index: 1038656 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1417. Min Act: -0.0003

Data Index: 1045752 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1466. Min Act: -0.0003

Data Index: 555126 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1393. Min Act: -0.0003

Data Index: 182005 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1338. Min Act: -0.0003

Data Index: 392827 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1494. Min Act: -0.0003

Data Index: 859110 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1363. Min Act: -0.0003

Data Index: 524283 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1408. Min Act: -0.0003

Data Index: 1108185 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1337. Min Act: -0.0003

Data Index: 755459 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1438. Min Act: -0.0003

Data Index: 387500 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1343. Min Act: -0.0003

Data Index: 447046 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1317. Min Act: -0.0003

Data Index: 1247602 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1312. Min Act: -0.0003

Data Index: 822951 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1310. Min Act: -0.0003

Data Index: 101735 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1365. Min Act: -0.0003

Data Index: 346908 (C4 (Web Text))

Max Activating Token Index: 520