Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1607 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.9435. Min Act: -0.0000

Data Index: 574484 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7500. Min Act: -0.0000

Data Index: 1382172 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.7601. Min Act: -0.0000

Data Index: 1569433 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6683. Min Act: -0.0000

Data Index: 321889 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6200. Min Act: 0.0000

Data Index: 1445160 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.6281. Min Act: -0.0000

Data Index: 189923 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5914. Min Act: -0.0000

Data Index: 624417 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.5832. Min Act: -0.0000

Data Index: 1113711 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.4676. Min Act: -0.0000

Data Index: 1191389 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.2786. Min Act: -0.0000

Data Index: 1032752 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.3981. Min Act: -0.0000

Data Index: 1303657 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.3450. Min Act: -0.0000

Data Index: 496219 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.3189. Min Act: 0.0000

Data Index: 1658586 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.1445. Min Act: 0.0000

Data Index: 691924 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.1368. Min Act: -0.0000

Data Index: 930373 (The Pile)

Max Activating Token Index: 376

Text #15

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.2880. Min Act: -0.0000

Data Index: 941024 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.2799. Min Act: -0.0000

Data Index: 1451066 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.4263. Min Act: 0.0000

Data Index: 1917400 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.2777. Min Act: -0.0000

Data Index: 1948158 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.3870. Min Act: -0.0000

Data Index: 1306537 (The Pile)

Max Activating Token Index: 616