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

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

Neuron 1428 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1637854 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.9218. Min Act: -0.0000

Data Index: 1510729 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1568033 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.2419. Min Act: -0.0000

Data Index: 1641261 (Python Code)

Max Activating Token Index: 786

Text #4

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.6352. Min Act: -0.0000

Data Index: 1494093 (Python Code)

Max Activating Token Index: 66

Text #5

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.6056. Min Act: -0.0000

Data Index: 1597052 (Python Code)

Max Activating Token Index: 525

Text #6

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.5061. Min Act: -0.0000

Data Index: 1408206 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.4036. Min Act: -0.0000

Data Index: 1419072 (Python Code)

Max Activating Token Index: 493

Text #8

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.5179. Min Act: -0.0000

Data Index: 1396251 (Python Code)

Max Activating Token Index: 601

Text #9

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.5054. Min Act: -0.0000

Data Index: 1412456 (Python Code)

Max Activating Token Index: 201

Text #10

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1568391 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1427265 (Python Code)

Max Activating Token Index: 222

Text #12

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1446063 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1588828 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1421225 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1453347 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.3469. Min Act: -0.0000

Data Index: 1486724 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1538482 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1389911 (Python Code)

Max Activating Token Index: 668

Text #19

Max Range: 1.9218. Min Range: -1.9218

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1424091 (Python Code)

Max Activating Token Index: 512