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

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

Neuron 6027 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: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1396911 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1481780 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1640118 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1477055 (Python Code)

Max Activating Token Index: 746

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1567618 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1421082 (Python Code)

Max Activating Token Index: 909

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1417394 (Python Code)

Max Activating Token Index: 655

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1460875 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0969. Min Act: -0.0001

Data Index: 832347 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1553962 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1368419 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1436599 (Python Code)

Max Activating Token Index: 727

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1369518 (Python Code)

Max Activating Token Index: 994

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1605968 (Python Code)

Max Activating Token Index: 858

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1438306 (Python Code)

Max Activating Token Index: 454

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1654803 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1630828 (Python Code)

Max Activating Token Index: 397

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0963. Min Act: -0.0001

Data Index: 761943 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1401486 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1651838 (Python Code)

Max Activating Token Index: 517