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

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

Neuron 2749 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1548942 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1020429 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1447. Min Act: -0.0001

Data Index: 166983 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1652917 (Python Code)

Max Activating Token Index: 937

Text #4

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1461. Min Act: -0.0001

Data Index: 339286 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1611043 (Python Code)

Max Activating Token Index: 968

Text #6

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1286. Min Act: -0.0001

Data Index: 608685 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1330. Min Act: -0.0001

Data Index: 29944 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1114871 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1294. Min Act: -0.0001

Data Index: 759885 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1291. Min Act: -0.0001

Data Index: 541735 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1329. Min Act: -0.0000

Data Index: 521811 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1434677 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1565441 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1473944 (Python Code)

Max Activating Token Index: 304

Text #15

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1148. Min Act: -0.0001

Data Index: 551537 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1299654 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1174. Min Act: -0.0001

Data Index: 19527 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1516807 (Python Code)

Max Activating Token Index: 261

Text #19

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1220. Min Act: -0.0001

Data Index: 664927 (C4 (Web Text))

Max Activating Token Index: 558