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

Dataset: The Pile

Neuron 1248 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.2991. Min Act: -0.0000

Data Index: 1511600 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9317. Min Act: -0.0000

Data Index: 88950 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9860. Min Act: -0.0000

Data Index: 971766 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9079. Min Act: -0.0000

Data Index: 286898 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1077857 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8970. Min Act: -0.0000

Data Index: 791606 (The Pile)

Max Activating Token Index: 581

Text #6

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1328047 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1294984 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8383. Min Act: -0.0000

Data Index: 424017 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1459453 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1755064 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8171. Min Act: -0.0000

Data Index: 773638 (The Pile)

Max Activating Token Index: 596

Text #12

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1495896 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7777. Min Act: -0.0000

Data Index: 459115 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1628656 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7007. Min Act: -0.0000

Data Index: 312338 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7367. Min Act: -0.0000

Data Index: 296093 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7178. Min Act: -0.0000

Data Index: 304513 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.6512. Min Act: -0.0000

Data Index: 976947 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1525454 (The Pile)

Max Activating Token Index: 983