Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 27 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2297. Min Act: -0.0001

Data Index: 966281 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1943. Min Act: -0.0001

Data Index: 517347 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1811. Min Act: -0.0001

Data Index: 301010 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1791. Min Act: -0.0001

Data Index: 330651 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1712. Min Act: -0.0001

Data Index: 788857 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1404. Min Act: -0.0001

Data Index: 83192 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1162588 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1417784 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1549. Min Act: -0.0001

Data Index: 544499 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1449. Min Act: -0.0001

Data Index: 461946 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1456. Min Act: -0.0001

Data Index: 128156 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1527. Min Act: -0.0000

Data Index: 872773 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1087701 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1436. Min Act: -0.0001

Data Index: 120528 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1439. Min Act: -0.0001

Data Index: 221817 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1162347 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1549. Min Act: -0.0001

Data Index: 665677 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1428. Min Act: -0.0001

Data Index: 517544 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1403281 (Python Code)

Max Activating Token Index: 176

Text #19

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1217. Min Act: -0.0001

Data Index: 899600 (C4 (Web Text))

Max Activating Token Index: 945