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

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

Neuron 1580 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3693. Min Act: -0.0001

Data Index: 1550492 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.4018. Min Act: -0.0001

Data Index: 1547501 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1477634 (Python Code)

Max Activating Token Index: 268

Text #3

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2863. Min Act: -0.0001

Data Index: 1541631 (Python Code)

Max Activating Token Index: 577

Text #4

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3204. Min Act: -0.0001

Data Index: 1585395 (Python Code)

Max Activating Token Index: 732

Text #5

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1374538 (Python Code)

Max Activating Token Index: 482

Text #6

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1475568 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1523131 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1457462 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2689. Min Act: -0.0001

Data Index: 1560435 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1561585 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1421117 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2160. Min Act: -0.0001

Data Index: 1485927 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1511981 (Python Code)

Max Activating Token Index: 485

Text #14

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1452746 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1583340 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2515. Min Act: -0.0001

Data Index: 1380697 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1411666 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2248. Min Act: -0.0001

Data Index: 1532979 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2518. Min Act: -0.0001

Data Index: 1535972 (Python Code)

Max Activating Token Index: 704