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

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

Neuron 4420 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.3702. Min Act: -0.0000

Data Index: 1472997 (Python Code)

Max Activating Token Index: 405

Text #1

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.3808. Min Act: -0.0000

Data Index: 1569871 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.1192. Min Act: -0.0000

Data Index: 1440665 (Python Code)

Max Activating Token Index: 196

Text #3

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.1087. Min Act: -0.0000

Data Index: 1480479 (Python Code)

Max Activating Token Index: 339

Text #4

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.1553. Min Act: -0.0000

Data Index: 1546553 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.1482. Min Act: -0.0000

Data Index: 1601027 (Python Code)

Max Activating Token Index: 1010

Text #6

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.0861. Min Act: -0.0000

Data Index: 1475139 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.0505. Min Act: -0.0000

Data Index: 1532408 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1398682 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 2.3808. Min Range: -2.3808

Max Act: 2.0069. Min Act: -0.0000

Data Index: 1476045 (Python Code)

Max Activating Token Index: 444

Text #10

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.9628. Min Act: -0.0000

Data Index: 1549181 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1540205 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.8967. Min Act: -0.0000

Data Index: 26645 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.8181. Min Act: -0.0000

Data Index: 1405685 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.8203. Min Act: -0.0000

Data Index: 1638786 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.8987. Min Act: -0.0000

Data Index: 739491 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.7828. Min Act: -0.0000

Data Index: 1472041 (Python Code)

Max Activating Token Index: 700

Text #17

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.6599. Min Act: -0.0000

Data Index: 1464504 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.6465. Min Act: -0.0000

Data Index: 836296 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 2.3808. Min Range: -2.3808

Max Act: 1.7313. Min Act: -0.0000

Data Index: 1589283 (Python Code)

Max Activating Token Index: 570