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

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

Neuron 3925 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: 1.2778. Min Range: -1.2778

Max Act: 1.2778. Min Act: 0.0001

Data Index: 1582528 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.7681. Min Act: -0.0000

Data Index: 417217 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.6917. Min Act: -0.0000

Data Index: 184897 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.7355. Min Act: -0.0000

Data Index: 605945 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.6420. Min Act: -0.0000

Data Index: 969358 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.6386. Min Act: -0.0000

Data Index: 478613 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.6335. Min Act: -0.0000

Data Index: 939142 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.6354. Min Act: -0.0000

Data Index: 334651 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1303663 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.6035. Min Act: -0.0000

Data Index: 314316 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.6101. Min Act: -0.0000

Data Index: 8989 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1299686 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5650. Min Act: -0.0000

Data Index: 464528 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1251989 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1329734 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5885. Min Act: -0.0000

Data Index: 488736 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5713. Min Act: -0.0000

Data Index: 166762 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5846. Min Act: 0.0000

Data Index: 953303 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5831. Min Act: -0.0000

Data Index: 823098 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.2778. Min Range: -1.2778

Max Act: 0.5839. Min Act: -0.0000

Data Index: 710118 (C4 (Web Text))

Max Activating Token Index: 539