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

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

Neuron 449 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.7831. Min Act: -0.0000

Data Index: 889761 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.6500. Min Act: -0.0000

Data Index: 75200 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.6516. Min Act: -0.0000

Data Index: 21434 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.3601. Min Act: -0.0000

Data Index: 357097 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.3153. Min Act: -0.0000

Data Index: 1581938 (Python Code)

Max Activating Token Index: 969

Text #5

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.1427. Min Act: -0.0000

Data Index: 78466 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.2357. Min Act: -0.0000

Data Index: 20907 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.0920. Min Act: -0.0000

Data Index: 1555051 (Python Code)

Max Activating Token Index: 623

Text #8

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.0719. Min Act: -0.0000

Data Index: 793123 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.0218. Min Act: -0.0000

Data Index: 1572254 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1567926 (Python Code)

Max Activating Token Index: 507

Text #11

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.0204. Min Act: -0.0000

Data Index: 469087 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 2.7831. Min Range: -2.7831

Max Act: 1.9805. Min Act: -0.0000

Data Index: 32053 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 2.7831. Min Range: -2.7831

Max Act: 1.8267. Min Act: -0.0000

Data Index: 1054745 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 2.7831. Min Range: -2.7831

Max Act: 2.0168. Min Act: -0.0000

Data Index: 1380885 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 2.7831. Min Range: -2.7831

Max Act: 1.9154. Min Act: -0.0000

Data Index: 1465470 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 2.7831. Min Range: -2.7831

Max Act: 1.8673. Min Act: -0.0000

Data Index: 1302627 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 2.7831. Min Range: -2.7831

Max Act: 1.9870. Min Act: -0.0000

Data Index: 1151238 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 2.7831. Min Range: -2.7831

Max Act: 1.8347. Min Act: -0.0000

Data Index: 521942 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 2.7831. Min Range: -2.7831

Max Act: 1.8144. Min Act: -0.0000

Data Index: 340845 (C4 (Web Text))

Max Activating Token Index: 48