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

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

Neuron 245 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: 2.7020. Min Range: -2.7020

Max Act: 2.7020. Min Act: -0.0000

Data Index: 1233047 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.6546. Min Act: 0.0000

Data Index: 928225 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.3814. Min Act: 0.0000

Data Index: 926278 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.4099. Min Act: 0.0000

Data Index: 1472125 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.3242. Min Act: -0.0000

Data Index: 1405926 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1648876 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1640992 (Python Code)

Max Activating Token Index: 310

Text #7

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1590817 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.1908. Min Act: 0.0000

Data Index: 5297 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1114874 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.1344. Min Act: 0.0001

Data Index: 935033 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.0608. Min Act: -0.0000

Data Index: 495078 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.0972. Min Act: -0.0000

Data Index: 642227 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.0506. Min Act: 0.0000

Data Index: 504761 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1117956 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.1121. Min Act: -0.0000

Data Index: 386218 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.0175. Min Act: -0.0000

Data Index: 1389611 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 2.7020. Min Range: -2.7020

Max Act: 1.0014. Min Act: -0.0000

Data Index: 530091 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 2.7020. Min Range: -2.7020

Max Act: 0.9305. Min Act: -0.0000

Data Index: 275767 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 2.7020. Min Range: -2.7020

Max Act: 0.8879. Min Act: 0.0000

Data Index: 1372442 (Python Code)

Max Activating Token Index: 940