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

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

Neuron 454 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: 0.2370. Min Range: -0.2370

Max Act: 0.2370. Min Act: -0.0000

Data Index: 267640 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1648. Min Act: -0.0000

Data Index: 840626 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1559. Min Act: -0.0000

Data Index: 908284 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1222875 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1404. Min Act: -0.0000

Data Index: 374411 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1356. Min Act: -0.0000

Data Index: 31513 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1342. Min Act: -0.0000

Data Index: 678376 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1440. Min Act: -0.0000

Data Index: 147595 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1527. Min Act: -0.0000

Data Index: 555347 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1389. Min Act: -0.0000

Data Index: 272037 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1499067 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1285. Min Act: -0.0000

Data Index: 268851 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1293. Min Act: -0.0000

Data Index: 510801 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1227219 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1122. Min Act: -0.0000

Data Index: 471116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1273. Min Act: -0.0000

Data Index: 410282 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1620053 (Python Code)

Max Activating Token Index: 92

Text #17

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1303. Min Act: -0.0000

Data Index: 440912 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1252760 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1176. Min Act: -0.0000

Data Index: 174239 (C4 (Web Text))

Max Activating Token Index: 399