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

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

Neuron 1080 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1620. Min Act: -0.0001

Data Index: 638058 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1397. Min Act: -0.0001

Data Index: 862591 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1438. Min Act: -0.0001

Data Index: 927794 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1453. Min Act: -0.0001

Data Index: 843821 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1418. Min Act: -0.0001

Data Index: 300689 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1168679 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1377. Min Act: -0.0001

Data Index: 798169 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1121901 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1390. Min Act: -0.0001

Data Index: 207509 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1004257 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1343. Min Act: -0.0001

Data Index: 649951 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1354. Min Act: -0.0001

Data Index: 95492 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1368. Min Act: -0.0001

Data Index: 281376 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1216. Min Act: -0.0001

Data Index: 653975 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1337. Min Act: -0.0001

Data Index: 559295 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1339. Min Act: -0.0001

Data Index: 132738 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1333. Min Act: -0.0001

Data Index: 227645 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1342. Min Act: -0.0001

Data Index: 123946 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1216. Min Act: -0.0001

Data Index: 614053 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1158. Min Act: -0.0001

Data Index: 671884 (C4 (Web Text))

Max Activating Token Index: 825