Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1071 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1343319 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1748. Min Act: -0.0001

Data Index: 771372 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1525. Min Act: -0.0001

Data Index: 10608 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1080177 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1414. Min Act: -0.0001

Data Index: 876721 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1163464 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1392. Min Act: -0.0000

Data Index: 860641 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1417. Min Act: -0.0001

Data Index: 466341 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1301. Min Act: -0.0001

Data Index: 332861 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1405. Min Act: -0.0001

Data Index: 758231 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1249. Min Act: -0.0001

Data Index: 88177 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1075163 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1146968 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1257827 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1277. Min Act: -0.0001

Data Index: 26527 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1218552 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1261. Min Act: -0.0001

Data Index: 836028 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1301. Min Act: -0.0001

Data Index: 317092 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1248. Min Act: -0.0001

Data Index: 518791 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1239. Min Act: -0.0001

Data Index: 877829 (C4 (Web Text))

Max Activating Token Index: 605