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

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

Neuron 1311 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.2001. Min Act: -0.0001

Data Index: 841988 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1698. Min Act: -0.0001

Data Index: 731811 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1356943 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1474. Min Act: -0.0001

Data Index: 20740 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1126299 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1514. Min Act: -0.0001

Data Index: 885196 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1510. Min Act: -0.0001

Data Index: 322018 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1330616 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1258888 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1356. Min Act: -0.0001

Data Index: 654350 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1522. Min Act: -0.0001

Data Index: 228925 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1443. Min Act: -0.0001

Data Index: 1307891 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1139524 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1347. Min Act: -0.0001

Data Index: 275981 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1392. Min Act: -0.0001

Data Index: 774588 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1295. Min Act: -0.0001

Data Index: 519377 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1331. Min Act: -0.0001

Data Index: 563188 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1319. Min Act: -0.0001

Data Index: 20356 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1331. Min Act: -0.0001

Data Index: 604797 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.2001. Min Range: -0.2001

Max Act: 0.1357. Min Act: -0.0001

Data Index: 235028 (C4 (Web Text))

Max Activating Token Index: 27