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

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

Neuron 2482 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1540. Min Act: -0.0001

Data Index: 964290 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1303064 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1069265 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1565. Min Act: -0.0001

Data Index: 747317 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1323484 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1435. Min Act: -0.0001

Data Index: 27387 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1445. Min Act: -0.0001

Data Index: 293432 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1486. Min Act: -0.0001

Data Index: 403226 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1509. Min Act: -0.0001

Data Index: 883782 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1497. Min Act: -0.0001

Data Index: 441700 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1008344 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1584. Min Act: -0.0001

Data Index: 45532 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1361. Min Act: -0.0001

Data Index: 815350 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1304. Min Act: -0.0001

Data Index: 722852 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1293. Min Act: -0.0001

Data Index: 394440 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1388. Min Act: -0.0001

Data Index: 725995 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1343. Min Act: -0.0001

Data Index: 690539 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1487. Min Act: -0.0001

Data Index: 826040 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1414. Min Act: -0.0001

Data Index: 578651 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1410. Min Act: -0.0001

Data Index: 829180 (C4 (Web Text))

Max Activating Token Index: 944