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

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

Neuron 1961 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: 1.2033. Min Range: -1.2033

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1482126 (Python Code)

Max Activating Token Index: 636

Text #1

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1557110 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1489958 (Python Code)

Max Activating Token Index: 973

Text #3

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1654527 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1647927 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1433144 (Python Code)

Max Activating Token Index: 542

Text #6

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1458156 (Python Code)

Max Activating Token Index: 209

Text #7

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1363669 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1541460 (Python Code)

Max Activating Token Index: 590

Text #9

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1639920 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1526732 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1448399 (Python Code)

Max Activating Token Index: 450

Text #12

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1477267 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1458852 (Python Code)

Max Activating Token Index: 294

Text #14

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1503299 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1390855 (Python Code)

Max Activating Token Index: 753

Text #16

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1459598 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1521981 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1478665 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 1.2033. Min Range: -1.2033

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1515985 (Python Code)

Max Activating Token Index: 370