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

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

Neuron 3145 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: 0.4302. Min Range: -0.4302

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1483862 (Python Code)

Max Activating Token Index: 274

Text #1

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1452362 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1471339 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1589643 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1476682 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1568468 (Python Code)

Max Activating Token Index: 553

Text #6

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1582079 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1509528 (Python Code)

Max Activating Token Index: 664

Text #8

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1649744 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1539007 (Python Code)

Max Activating Token Index: 603

Text #10

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1411702 (Python Code)

Max Activating Token Index: 375

Text #11

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1377133 (Python Code)

Max Activating Token Index: 495

Text #12

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1608521 (Python Code)

Max Activating Token Index: 226

Text #13

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1439415 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1596316 (Python Code)

Max Activating Token Index: 397

Text #15

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1624876 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1643747 (Python Code)

Max Activating Token Index: 478

Text #17

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1619103 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1459066 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.4302. Min Range: -0.4302

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1410499 (Python Code)

Max Activating Token Index: 303