Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2561 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.9085. Min Range: -8.9085

Max Act: 8.1439. Min Act: -0.0000

Data Index: 499428 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 8.9085. Min Range: -8.9085

Max Act: 8.5450. Min Act: -0.0000

Data Index: 1101452 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 8.9085. Min Range: -8.9085

Max Act: 8.9085. Min Act: -0.0000

Data Index: 1214393 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 8.9085. Min Range: -8.9085

Max Act: 8.2100. Min Act: -0.0000

Data Index: 1143934 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 8.9085. Min Range: -8.9085

Max Act: 8.1314. Min Act: -0.0000

Data Index: 1323030 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.4367. Min Act: -0.0000

Data Index: 1157474 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.4669. Min Act: -0.0000

Data Index: 266385 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.6293. Min Act: -0.0000

Data Index: 529344 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.6311. Min Act: -0.0000

Data Index: 57299 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.7032. Min Act: -0.0000

Data Index: 326680 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.5114. Min Act: -0.0000

Data Index: 1012068 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.2921. Min Act: -0.0000

Data Index: 1020350 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.1406. Min Act: -0.0000

Data Index: 635139 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.0682. Min Act: -0.0000

Data Index: 646774 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.1942. Min Act: -0.0000

Data Index: 578601 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.0427. Min Act: -0.0000

Data Index: 1287739 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 8.9085. Min Range: -8.9085

Max Act: 6.7625. Min Act: -0.0000

Data Index: 251425 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.1453. Min Act: -0.0000

Data Index: 911935 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 8.9085. Min Range: -8.9085

Max Act: 7.1620. Min Act: -0.0000

Data Index: 141413 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 8.9085. Min Range: -8.9085

Max Act: 6.2094. Min Act: -0.0000

Data Index: 471902 (C4 (Web Text))

Max Activating Token Index: 751