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

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

Neuron 4855 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4326. Min Act: -0.0000

Data Index: 985044 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1117388 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4279. Min Act: -0.0000

Data Index: 15086 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1256814 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3936. Min Act: -0.0000

Data Index: 299862 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1105329 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3404. Min Act: -0.0000

Data Index: 564619 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3507. Min Act: -0.0000

Data Index: 67981 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3514. Min Act: -0.0000

Data Index: 636652 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3679. Min Act: -0.0000

Data Index: 146831 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1219363 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3506. Min Act: -0.0000

Data Index: 446920 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3250. Min Act: -0.0000

Data Index: 548814 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3385. Min Act: -0.0000

Data Index: 888949 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3467. Min Act: -0.0000

Data Index: 88850 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3001. Min Act: -0.0000

Data Index: 948368 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3205. Min Act: -0.0000

Data Index: 596553 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3206. Min Act: -0.0000

Data Index: 969194 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.2928. Min Act: -0.0000

Data Index: 101205 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.4435. Min Range: -0.4435

Max Act: 0.3012. Min Act: -0.0000

Data Index: 894685 (C4 (Web Text))

Max Activating Token Index: 346