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

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

Neuron 2868 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.9038. Min Act: -0.0000

Data Index: 1491623 (Python Code)

Max Activating Token Index: 726

Text #1

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.8452. Min Act: -0.0000

Data Index: 1540944 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.7969. Min Act: -0.0000

Data Index: 1484546 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.3496. Min Act: -0.0000

Data Index: 1504263 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.2752. Min Act: -0.0000

Data Index: 1377699 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.3929. Min Act: -0.0000

Data Index: 1398050 (Python Code)

Max Activating Token Index: 193

Text #6

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.1893. Min Act: -0.0000

Data Index: 1578287 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.1457. Min Act: -0.0000

Data Index: 1567183 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.4467. Min Act: -0.0000

Data Index: 1578982 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.2584. Min Act: -0.0000

Data Index: 1520895 (Python Code)

Max Activating Token Index: 123

Text #10

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.3513. Min Act: -0.0000

Data Index: 1619878 (Python Code)

Max Activating Token Index: 985

Text #11

Max Range: 4.9038. Min Range: -4.9038

Max Act: 4.1285. Min Act: -0.0000

Data Index: 719678 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 4.9038. Min Range: -4.9038

Max Act: 3.9424. Min Act: -0.0000

Data Index: 1601528 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 4.9038. Min Range: -4.9038

Max Act: 3.7039. Min Act: -0.0000

Data Index: 1026622 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 4.9038. Min Range: -4.9038

Max Act: 3.9119. Min Act: -0.0000

Data Index: 1399029 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 4.9038. Min Range: -4.9038

Max Act: 3.5920. Min Act: -0.0000

Data Index: 1498049 (Python Code)

Max Activating Token Index: 944

Text #16

Max Range: 4.9038. Min Range: -4.9038

Max Act: 3.3868. Min Act: -0.0000

Data Index: 23250 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 4.9038. Min Range: -4.9038

Max Act: 3.6588. Min Act: -0.0000

Data Index: 1621251 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 4.9038. Min Range: -4.9038

Max Act: 3.6230. Min Act: -0.0000

Data Index: 1473060 (Python Code)

Max Activating Token Index: 792

Text #19

Max Range: 4.9038. Min Range: -4.9038

Max Act: 3.7832. Min Act: -0.0000

Data Index: 1644514 (Python Code)

Max Activating Token Index: 629