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

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

Neuron 1969 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: 2.8298. Min Range: -2.8298

Max Act: 2.8298. Min Act: -0.0000

Data Index: 183368 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 2.8298. Min Range: -2.8298

Max Act: 2.5964. Min Act: 0.0000

Data Index: 972525 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 2.8298. Min Range: -2.8298

Max Act: 2.4487. Min Act: -0.0000

Data Index: 463727 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.8298. Min Range: -2.8298

Max Act: 2.1894. Min Act: 0.0000

Data Index: 376614 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.9740. Min Act: -0.0000

Data Index: 383890 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.9479. Min Act: -0.0000

Data Index: 862478 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 2.8298. Min Range: -2.8298

Max Act: 2.0462. Min Act: 0.0000

Data Index: 517089 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 2.8298. Min Range: -2.8298

Max Act: 2.0699. Min Act: 0.0000

Data Index: 118686 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.9071. Min Act: 0.0000

Data Index: 1065633 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.8760. Min Act: -0.0000

Data Index: 182412 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.7304. Min Act: 0.0000

Data Index: 622736 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.6710. Min Act: 0.0000

Data Index: 616064 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.6475. Min Act: -0.0000

Data Index: 247948 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.5473. Min Act: 0.0000

Data Index: 513329 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.5322. Min Act: -0.0000

Data Index: 471964 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.7161. Min Act: -0.0000

Data Index: 461220 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.5223. Min Act: -0.0000

Data Index: 948553 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.5844. Min Act: 0.0000

Data Index: 1173789 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.5850. Min Act: 0.0000

Data Index: 1327868 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 2.8298. Min Range: -2.8298

Max Act: 1.4984. Min Act: 0.0000

Data Index: 17939 (C4 (Web Text))

Max Activating Token Index: 83