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

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

Neuron 2596 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1535687 (Python Code)

Max Activating Token Index: 317

Text #1

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1464567 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1390533 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1436280 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1444132 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1519570 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1624970 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1509200 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1414372 (Python Code)

Max Activating Token Index: 429

Text #9

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1424078 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1486453 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1507807 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1514363 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1504540 (Python Code)

Max Activating Token Index: 193

Text #14

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1610167 (Python Code)

Max Activating Token Index: 786

Text #15

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1360392 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1564824 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1649557 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1428613 (Python Code)

Max Activating Token Index: 460

Text #19

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0870. Min Act: -0.0000

Data Index: 996515 (C4 (Web Text))

Max Activating Token Index: 452