Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 933 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1414607 (Python Code)

Max Activating Token Index: 561

Text #1

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1575636 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1507070 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1595126 (Python Code)

Max Activating Token Index: 582

Text #4

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1597616 (Python Code)

Max Activating Token Index: 539

Text #5

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1601924 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1493797 (Python Code)

Max Activating Token Index: 389

Text #7

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1484478 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1481248 (Python Code)

Max Activating Token Index: 441

Text #9

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1369704 (Python Code)

Max Activating Token Index: 974

Text #10

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1397459 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1610552 (Python Code)

Max Activating Token Index: 482

Text #12

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1613648 (Python Code)

Max Activating Token Index: 754

Text #13

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1624402 (Python Code)

Max Activating Token Index: 934

Text #14

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1504134 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1480967 (Python Code)

Max Activating Token Index: 507

Text #16

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1493328 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1593182 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1636669 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 0.4931. Min Range: -0.4931

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1498976 (Python Code)

Max Activating Token Index: 894