Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2336 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1050608 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1506. Min Act: -0.0000

Data Index: 357445 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1494. Min Act: -0.0000

Data Index: 198384 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1379. Min Act: -0.0000

Data Index: 7887 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1373. Min Act: -0.0000

Data Index: 294851 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1499. Min Act: 0.0000

Data Index: 1398186 (Python Code)

Max Activating Token Index: 757

Text #6

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1400. Min Act: -0.0000

Data Index: 800953 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1432. Min Act: -0.0000

Data Index: 368057 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1183028 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1340. Min Act: -0.0000

Data Index: 770189 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1005326 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1248. Min Act: -0.0000

Data Index: 578904 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1279. Min Act: -0.0000

Data Index: 342180 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1211. Min Act: -0.0000

Data Index: 19636 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1179. Min Act: -0.0000

Data Index: 763278 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1228. Min Act: -0.0000

Data Index: 202189 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1260. Min Act: -0.0000

Data Index: 515668 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1187465 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1185. Min Act: -0.0000

Data Index: 387277 (C4 (Web Text))

Max Activating Token Index: 974