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

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

Neuron 913 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: 1.5184. Min Range: -1.5184

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1456272 (Python Code)

Max Activating Token Index: 348

Text #1

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.5184. Min Act: -0.0000

Data Index: 1581168 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.4862. Min Act: -0.0000

Data Index: 1513341 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1603214 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1614891 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.3809. Min Act: -0.0000

Data Index: 1434660 (Python Code)

Max Activating Token Index: 96

Text #6

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1564012 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1553808 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1496513 (Python Code)

Max Activating Token Index: 148

Text #9

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.3350. Min Act: -0.0000

Data Index: 1408161 (Python Code)

Max Activating Token Index: 411

Text #10

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1388212 (Python Code)

Max Activating Token Index: 919

Text #11

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1422580 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1456368 (Python Code)

Max Activating Token Index: 563

Text #13

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2938. Min Act: -0.0000

Data Index: 1502455 (Python Code)

Max Activating Token Index: 85

Text #14

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.3255. Min Act: -0.0000

Data Index: 1417177 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2087. Min Act: -0.0000

Data Index: 1432847 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1592969 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1630225 (Python Code)

Max Activating Token Index: 616

Text #18

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.3332. Min Act: -0.0000

Data Index: 1594209 (Python Code)

Max Activating Token Index: 811

Text #19

Max Range: 1.5184. Min Range: -1.5184

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1650883 (Python Code)

Max Activating Token Index: 604