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

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

Neuron 3473 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: 0.1774. Min Range: -0.1774

Max Act: 0.1727. Min Act: -0.0001

Data Index: 948476 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1696. Min Act: -0.0001

Data Index: 183888 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1774. Min Act: -0.0001

Data Index: 758668 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1289090 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1617. Min Act: -0.0001

Data Index: 175571 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1494. Min Act: -0.0001

Data Index: 93649 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1547. Min Act: -0.0001

Data Index: 1314680 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1039234 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1452. Min Act: -0.0001

Data Index: 581035 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1310. Min Act: -0.0001

Data Index: 871934 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1356. Min Act: -0.0001

Data Index: 596774 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1283. Min Act: -0.0001

Data Index: 548610 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1355959 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1256. Min Act: -0.0001

Data Index: 318197 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1329. Min Act: -0.0001

Data Index: 94111 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1150. Min Act: -0.0001

Data Index: 724003 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1200132 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1229. Min Act: -0.0001

Data Index: 441552 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1260. Min Act: -0.0001

Data Index: 75043 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1215. Min Act: -0.0001

Data Index: 417907 (C4 (Web Text))

Max Activating Token Index: 248