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

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

Neuron 6085 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2725. Min Act: -0.0000

Data Index: 781940 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1356726 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1028469 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1796. Min Act: -0.0000

Data Index: 12611 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1724. Min Act: -0.0000

Data Index: 871720 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1534. Min Act: -0.0000

Data Index: 230594 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1343. Min Act: -0.0000

Data Index: 254356 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1517. Min Act: -0.0000

Data Index: 374252 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1185407 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1387. Min Act: -0.0000

Data Index: 56425 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1349. Min Act: -0.0000

Data Index: 908410 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1436. Min Act: -0.0000

Data Index: 333179 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1472. Min Act: -0.0000

Data Index: 366220 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1247674 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1325123 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1217. Min Act: -0.0000

Data Index: 229910 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1277993 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1226528 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1281. Min Act: -0.0000

Data Index: 801149 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1327. Min Act: -0.0000

Data Index: 661134 (C4 (Web Text))

Max Activating Token Index: 774