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

Dataset: The Pile

Neuron 2248 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.9955. Min Act: -0.0000

Data Index: 389059 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.9170. Min Act: -0.0000

Data Index: 1245118 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7358. Min Act: -0.0000

Data Index: 261424 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5936. Min Act: -0.0000

Data Index: 653320 (The Pile)

Max Activating Token Index: 747

Text #4

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1413144 (The Pile)

Max Activating Token Index: 810

Text #5

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1646838 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1789993 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1533413 (The Pile)

Max Activating Token Index: 451

Text #8

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.3788. Min Act: 0.0000

Data Index: 953972 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.2283. Min Act: -0.0000

Data Index: 944121 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.1029. Min Act: -0.0000

Data Index: 347151 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.2211. Min Act: -0.0000

Data Index: 118823 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1548622 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 1.9955. Min Range: -1.9955

Max Act: 0.9991. Min Act: -0.0000

Data Index: 884390 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1709378 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1094152 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1219958 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1521798 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1536318 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1098545 (The Pile)

Max Activating Token Index: 227