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

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

Neuron 5298 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1549753 (Python Code)

Max Activating Token Index: 695

Text #1

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1417742 (Python Code)

Max Activating Token Index: 779

Text #2

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1417909 (Python Code)

Max Activating Token Index: 696

Text #3

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1422797 (Python Code)

Max Activating Token Index: 847

Text #4

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1377518 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1370874 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1462785 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5596. Min Act: 0.0000

Data Index: 914840 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1395915 (Python Code)

Max Activating Token Index: 731

Text #9

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1434168 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4765. Min Act: -0.0000

Data Index: 309865 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5084. Min Act: -0.0000

Data Index: 841425 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1523160 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1445148 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1601665 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1570246 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4399. Min Act: -0.0000

Data Index: 822056 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1641385 (Python Code)

Max Activating Token Index: 710

Text #18

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1615978 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 0.7670. Min Range: -0.7670

Max Act: 0.3939. Min Act: -0.0000

Data Index: 636566 (C4 (Web Text))

Max Activating Token Index: 273