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

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

Neuron 173 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.9545. Min Act: -0.0000

Data Index: 1532944 (Python Code)

Max Activating Token Index: 408

Text #1

Max Range: 3.0653. Min Range: -3.0653

Max Act: 3.0653. Min Act: -0.0001

Data Index: 1410863 (Python Code)

Max Activating Token Index: 740

Text #2

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.6827. Min Act: -0.0000

Data Index: 1585575 (Python Code)

Max Activating Token Index: 157

Text #3

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.8038. Min Act: -0.0001

Data Index: 1507919 (Python Code)

Max Activating Token Index: 591

Text #4

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.8694. Min Act: -0.0001

Data Index: 1628089 (Python Code)

Max Activating Token Index: 467

Text #5

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.8533. Min Act: -0.0000

Data Index: 1568595 (Python Code)

Max Activating Token Index: 678

Text #6

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.5671. Min Act: -0.0001

Data Index: 1399995 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.6883. Min Act: -0.0000

Data Index: 1504728 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.4143. Min Act: -0.0001

Data Index: 1370731 (Python Code)

Max Activating Token Index: 300

Text #9

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.5167. Min Act: -0.0001

Data Index: 1589081 (Python Code)

Max Activating Token Index: 118

Text #10

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.5056. Min Act: -0.0001

Data Index: 1485075 (Python Code)

Max Activating Token Index: 611

Text #11

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.6236. Min Act: -0.0000

Data Index: 1641473 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.2832. Min Act: -0.0001

Data Index: 1592143 (Python Code)

Max Activating Token Index: 761

Text #13

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.4692. Min Act: -0.0001

Data Index: 1363826 (Python Code)

Max Activating Token Index: 900

Text #14

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.6961. Min Act: -0.0001

Data Index: 1559621 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.4709. Min Act: -0.0001

Data Index: 1390982 (Python Code)

Max Activating Token Index: 663

Text #16

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.7026. Min Act: -0.0000

Data Index: 1377022 (Python Code)

Max Activating Token Index: 303

Text #17

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.4386. Min Act: -0.0000

Data Index: 1528041 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.5419. Min Act: -0.0000

Data Index: 1587528 (Python Code)

Max Activating Token Index: 329

Text #19

Max Range: 3.0653. Min Range: -3.0653

Max Act: 2.5553. Min Act: -0.0001

Data Index: 1370007 (Python Code)

Max Activating Token Index: 623