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

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

Neuron 5881 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.9483. Min Act: -0.0001

Data Index: 1422445 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.9483. Min Act: -0.0001

Data Index: 1535302 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1534346 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.8233. Min Act: -0.0001

Data Index: 1440889 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7209. Min Act: -0.0001

Data Index: 1381142 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7246. Min Act: -0.0001

Data Index: 1383965 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7246. Min Act: -0.0001

Data Index: 1587649 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.7246. Min Act: -0.0001

Data Index: 1486449 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1392007 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1379277 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.5892. Min Act: -0.0001

Data Index: 1443453 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.5863. Min Act: -0.0001

Data Index: 1476585 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.5474. Min Act: -0.0001

Data Index: 1584923 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.5831. Min Act: -0.0001

Data Index: 1448112 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1400965 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1415050 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1574552 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1515151 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1616237 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.9483. Min Range: -0.9483

Max Act: 0.5654. Min Act: -0.0001

Data Index: 1522876 (Python Code)

Max Activating Token Index: 9