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

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

Neuron 1645 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: 0.8482. Min Range: -0.8482

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1444331 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7489. Min Act: -0.0000

Data Index: 433881 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7381. Min Act: -0.0000

Data Index: 494388 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7107. Min Act: -0.0000

Data Index: 730600 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1400912 (Python Code)

Max Activating Token Index: 670

Text #5

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7088. Min Act: 0.0000

Data Index: 316962 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6685. Min Act: -0.0000

Data Index: 172862 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1608337 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1498020 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1528247 (Python Code)

Max Activating Token Index: 715

Text #10

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1428510 (Python Code)

Max Activating Token Index: 237

Text #11

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6377. Min Act: -0.0000

Data Index: 564441 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1281564 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.5875. Min Act: -0.0000

Data Index: 232545 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1436127 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1627363 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1541199 (Python Code)

Max Activating Token Index: 118

Text #17

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1515218 (Python Code)

Max Activating Token Index: 146

Text #18

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1598757 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.5952. Min Act: 0.0000

Data Index: 142248 (C4 (Web Text))

Max Activating Token Index: 796