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

Dataset: The Pile

Neuron 2180 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1173189 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1406091 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1477757 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1453364 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1367. Min Act: -0.0000

Data Index: 871987 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1347. Min Act: -0.0000

Data Index: 91912 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1317. Min Act: -0.0000

Data Index: 252881 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1269. Min Act: -0.0000

Data Index: 363626 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1874720 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1264. Min Act: -0.0000

Data Index: 586817 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1343. Min Act: -0.0000

Data Index: 105345 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1783402 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1446890 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1165657 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1239. Min Act: -0.0000

Data Index: 238139 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1281. Min Act: -0.0000

Data Index: 735382 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1935235 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1589736 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1186. Min Act: -0.0000

Data Index: 985859 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1569758 (The Pile)

Max Activating Token Index: 801