Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1174 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1324. Min Act: -0.0001

Data Index: 233704 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1164705 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1416. Min Act: -0.0001

Data Index: 278285 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1398. Min Act: -0.0001

Data Index: 272909 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1343. Min Act: -0.0001

Data Index: 553530 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1108012 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1359. Min Act: -0.0001

Data Index: 779319 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1334. Min Act: -0.0001

Data Index: 23980 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1291. Min Act: -0.0001

Data Index: 301936 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1397. Min Act: -0.0001

Data Index: 454261 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1176703 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1288. Min Act: -0.0001

Data Index: 546348 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1294. Min Act: -0.0001

Data Index: 19704 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1572640 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1130070 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1439861 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1212. Min Act: -0.0001

Data Index: 923517 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1391481 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1256. Min Act: -0.0001

Data Index: 605631 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1211. Min Act: -0.0001

Data Index: 736389 (C4 (Web Text))

Max Activating Token Index: 705