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

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

Neuron 4905 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1325650 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1588. Min Act: -0.0001

Data Index: 169280 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1540. Min Act: -0.0001

Data Index: 28298 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1529. Min Act: -0.0001

Data Index: 28344 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1506. Min Act: -0.0001

Data Index: 521823 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1060710 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1239376 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1398. Min Act: -0.0001

Data Index: 431015 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1343. Min Act: -0.0001

Data Index: 824202 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1441. Min Act: -0.0001

Data Index: 55844 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1341570 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1293. Min Act: -0.0001

Data Index: 709088 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1469. Min Act: -0.0001

Data Index: 488466 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1157419 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1308. Min Act: -0.0001

Data Index: 236063 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1003302 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1278. Min Act: -0.0001

Data Index: 566472 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1326. Min Act: -0.0001

Data Index: 154291 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1234500 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.1588. Min Range: -0.1588

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1209582 (C4 (Web Text))

Max Activating Token Index: 578