Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2698. Min Act: -0.0000

Data Index: 271130 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1125578 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1284583 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2234. Min Act: -0.0000

Data Index: 532038 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1154056 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1266434 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1013174 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2016. Min Act: -0.0000

Data Index: 616778 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1971. Min Act: -0.0000

Data Index: 128774 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1024375 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2088. Min Act: -0.0000

Data Index: 499260 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1942. Min Act: -0.0000

Data Index: 458122 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1922. Min Act: -0.0000

Data Index: 160232 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1786. Min Act: -0.0000

Data Index: 172455 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1920. Min Act: -0.0000

Data Index: 751739 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1296334 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1839. Min Act: -0.0000

Data Index: 904829 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1815. Min Act: -0.0000

Data Index: 125635 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1938. Min Act: -0.0000

Data Index: 56365 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1855. Min Act: -0.0000

Data Index: 651406 (C4 (Web Text))

Max Activating Token Index: 309