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

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

Neuron 3476 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1409378 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4821. Min Act: -0.0000

Data Index: 123026 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1475936 (Python Code)

Max Activating Token Index: 306

Text #3

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1634464 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1584024 (Python Code)

Max Activating Token Index: 910

Text #5

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1648617 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1426076 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1498924 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1490042 (Python Code)

Max Activating Token Index: 1009

Text #9

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1504930 (Python Code)

Max Activating Token Index: 372

Text #10

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1645632 (Python Code)

Max Activating Token Index: 542

Text #11

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1471932 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1504442 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1366051 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1485928 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1402768 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1533675 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1504009 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1465274 (Python Code)

Max Activating Token Index: 321

Text #19

Max Range: 0.5213. Min Range: -0.5213

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1579564 (Python Code)

Max Activating Token Index: 30