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

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

Neuron 1560 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.1348. Min Act: -0.0000

Data Index: 1508624 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.7370. Min Act: -0.0000

Data Index: 1518753 (Python Code)

Max Activating Token Index: 907

Text #2

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3009. Min Act: -0.0000

Data Index: 1429449 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.6932. Min Act: -0.0000

Data Index: 1482548 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.7694. Min Act: -0.0000

Data Index: 1421811 (Python Code)

Max Activating Token Index: 165

Text #5

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.0668. Min Act: -0.0000

Data Index: 1362214 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.6605. Min Act: -0.0000

Data Index: 1429316 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.7530. Min Act: -0.0000

Data Index: 1399741 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.5391. Min Act: -0.0000

Data Index: 1416608 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1593973 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.4649. Min Act: -0.0000

Data Index: 1619159 (Python Code)

Max Activating Token Index: 895

Text #11

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.8812. Min Act: -0.0000

Data Index: 1522770 (Python Code)

Max Activating Token Index: 802

Text #12

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.7712. Min Act: -0.0000

Data Index: 1555473 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.3987. Min Act: -0.0000

Data Index: 1514187 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.6422. Min Act: -0.0000

Data Index: 1164574 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.5552. Min Act: -0.0000

Data Index: 1485224 (Python Code)

Max Activating Token Index: 864

Text #16

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.5232. Min Act: -0.0000

Data Index: 1516726 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.5094. Min Act: -0.0000

Data Index: 1536976 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.4930. Min Act: -0.0000

Data Index: 1655172 (Python Code)

Max Activating Token Index: 432

Text #19

Max Range: 3.7370. Min Range: -3.7370

Max Act: 2.4354. Min Act: -0.0000

Data Index: 1404775 (Python Code)

Max Activating Token Index: 813