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

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

Neuron 5478 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.5388. Min Act: -0.0000

Data Index: 44616 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.5451. Min Act: -0.0000

Data Index: 300521 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.5644. Min Act: -0.0000

Data Index: 605030 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.4042. Min Act: -0.0000

Data Index: 932515 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.3798. Min Act: -0.0000

Data Index: 721881 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.2803. Min Act: 0.0000

Data Index: 259616 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.2214. Min Act: -0.0000

Data Index: 1045478 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.1477. Min Act: -0.0000

Data Index: 24277 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.2818. Min Act: -0.0000

Data Index: 282340 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.2304. Min Act: -0.0000

Data Index: 733161 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.2860. Min Act: -0.0000

Data Index: 609443 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.1941. Min Act: -0.0000

Data Index: 260693 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.2270. Min Act: -0.0000

Data Index: 407155 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.0791. Min Act: -0.0000

Data Index: 790941 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.0918. Min Act: -0.0000

Data Index: 355225 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1079215 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.1324. Min Act: -0.0000

Data Index: 381382 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 2.5644. Min Range: -2.5644

Max Act: 2.3371. Min Act: -0.0000

Data Index: 442965 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 2.5644. Min Range: -2.5644

Max Act: 1.9427. Min Act: -0.0000

Data Index: 752975 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 2.5644. Min Range: -2.5644

Max Act: 1.9882. Min Act: -0.0000

Data Index: 1481650 (Python Code)

Max Activating Token Index: 253