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

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

Neuron 2616 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1326. Min Range: -1.1326

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1384789 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1160276 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1538157 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1478949 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1392380 (Python Code)

Max Activating Token Index: 275

Text #5

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8913. Min Act: -0.0000

Data Index: 36174 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1451850 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8647. Min Act: -0.0000

Data Index: 620163 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1059924 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7863. Min Act: -0.0000

Data Index: 338670 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7422. Min Act: -0.0000

Data Index: 353521 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8316. Min Act: -0.0000

Data Index: 752707 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1405253 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1507235 (Python Code)

Max Activating Token Index: 782

Text #14

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7956. Min Act: -0.0000

Data Index: 68087 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7715. Min Act: -0.0000

Data Index: 36101 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1555574 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1311515 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1561742 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.6923. Min Act: -0.0000

Data Index: 509103 (C4 (Web Text))

Max Activating Token Index: 787