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

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

Neuron 4213 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.2545. Min Act: -0.0001

Data Index: 1575955 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 1.2545. Min Range: -1.2545

Max Act: 1.0227. Min Act: -0.0001

Data Index: 1421954 (Python Code)

Max Activating Token Index: 323

Text #2

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.8961. Min Act: -0.0001

Data Index: 1495356 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.9292. Min Act: -0.0001

Data Index: 1432747 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.9074. Min Act: -0.0001

Data Index: 1621038 (Python Code)

Max Activating Token Index: 137

Text #5

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.9901. Min Act: -0.0001

Data Index: 1635837 (Python Code)

Max Activating Token Index: 278

Text #6

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.9101. Min Act: -0.0001

Data Index: 1507006 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.9016. Min Act: -0.0001

Data Index: 1361965 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.8937. Min Act: -0.0001

Data Index: 1656180 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.8450. Min Act: -0.0001

Data Index: 1407668 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1360280 (Python Code)

Max Activating Token Index: 864

Text #11

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1640819 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.8005. Min Act: -0.0001

Data Index: 1579149 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1534805 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.7892. Min Act: -0.0001

Data Index: 1461649 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.7667. Min Act: -0.0001

Data Index: 1510116 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.7579. Min Act: -0.0001

Data Index: 1633404 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.8018. Min Act: -0.0001

Data Index: 1382899 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1439403 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 1.2545. Min Range: -1.2545

Max Act: 0.7796. Min Act: -0.0001

Data Index: 1422142 (Python Code)

Max Activating Token Index: 135