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

Dataset: The Pile

Neuron 775 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.7480. Min Act: -0.0000

Data Index: 439055 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.2991. Min Act: -0.0000

Data Index: 1874204 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 1.7480. Min Range: -1.7480

Max Act: 1.0131. Min Act: -0.0000

Data Index: 84659 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1052421 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1829057 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.9072. Min Act: -0.0000

Data Index: 755510 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1001580 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.9135. Min Act: -0.0000

Data Index: 14210 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.9130. Min Act: -0.0000

Data Index: 217602 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1710888 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1023304 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1093277 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8366. Min Act: -0.0000

Data Index: 482499 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1269250 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8397. Min Act: -0.0000

Data Index: 366265 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8312. Min Act: -0.0000

Data Index: 647611 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8044. Min Act: -0.0000

Data Index: 455280 (The Pile)

Max Activating Token Index: 692

Text #17

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1796342 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1186454 (The Pile)

Max Activating Token Index: 960

Text #19

Max Range: 1.7480. Min Range: -1.7480

Max Act: 0.8301. Min Act: -0.0000

Data Index: 563661 (The Pile)

Max Activating Token Index: 976