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

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

Neuron 5368 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: 1.3305. Min Range: -1.3305

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1432028 (Python Code)

Max Activating Token Index: 86

Text #1

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1645323 (Python Code)

Max Activating Token Index: 207

Text #2

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1628089 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1383719 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1623221 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1445714 (Python Code)

Max Activating Token Index: 296

Text #6

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1503693 (Python Code)

Max Activating Token Index: 754

Text #7

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1426061 (Python Code)

Max Activating Token Index: 160

Text #8

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1382203 (Python Code)

Max Activating Token Index: 571

Text #9

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0371. Min Act: -0.0000

Data Index: 1480391 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1642901 (Python Code)

Max Activating Token Index: 278

Text #11

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1578173 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1495979 (Python Code)

Max Activating Token Index: 336

Text #13

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1371656 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1495397 (Python Code)

Max Activating Token Index: 730

Text #15

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1529201 (Python Code)

Max Activating Token Index: 868

Text #16

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1655152 (Python Code)

Max Activating Token Index: 927

Text #17

Max Range: 1.3305. Min Range: -1.3305

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1433273 (Python Code)

Max Activating Token Index: 310

Text #18

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1558878 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 1.3305. Min Range: -1.3305

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1371575 (Python Code)

Max Activating Token Index: 382