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

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

Neuron 1534 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1723. Min Act: -0.0000

Data Index: 764410 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1845. Min Act: -0.0001

Data Index: 1192312 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1592. Min Act: -0.0001

Data Index: 192869 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1420. Min Act: -0.0001

Data Index: 631192 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1652. Min Act: -0.0000

Data Index: 628314 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1525406 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1173746 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1481. Min Act: -0.0000

Data Index: 566958 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1340. Min Act: -0.0000

Data Index: 983091 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1343. Min Act: -0.0000

Data Index: 379071 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1262. Min Act: -0.0000

Data Index: 621063 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1191301 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1314. Min Act: -0.0000

Data Index: 693005 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1152. Min Act: -0.0001

Data Index: 411851 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1116713 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1261. Min Act: -0.0000

Data Index: 410562 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1186. Min Act: -0.0000

Data Index: 646752 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1062199 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1132. Min Act: -0.0000

Data Index: 833451 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1243. Min Act: -0.0000

Data Index: 166021 (C4 (Web Text))

Max Activating Token Index: 979