Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 686 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0001

Data Index: 358059 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1310802 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1503. Min Act: -0.0001

Data Index: 1050849 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1508. Min Act: -0.0001

Data Index: 727285 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1420. Min Act: -0.0001

Data Index: 934392 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1190595 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1461. Min Act: -0.0001

Data Index: 567585 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1093523 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1558. Min Act: -0.0001

Data Index: 182841 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1537. Min Act: -0.0001

Data Index: 800023 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1282762 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1432. Min Act: -0.0001

Data Index: 675109 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1390. Min Act: -0.0001

Data Index: 962361 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1178312 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1397. Min Act: -0.0001

Data Index: 717735 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1351. Min Act: -0.0001

Data Index: 299591 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1388. Min Act: -0.0001

Data Index: 518899 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1349181 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1292. Min Act: -0.0001

Data Index: 1275919 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1455. Min Act: -0.0001

Data Index: 646190 (C4 (Web Text))

Max Activating Token Index: 940