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

Dataset: The Pile

Neuron 1952 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: 3.7079. Min Range: -3.7079

Max Act: 3.7079. Min Act: -0.0000

Data Index: 643677 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 3.7079. Min Range: -3.7079

Max Act: 2.4654. Min Act: -0.0000

Data Index: 1284010 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 3.7079. Min Range: -3.7079

Max Act: 2.1857. Min Act: -0.0000

Data Index: 1666637 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 3.7079. Min Range: -3.7079

Max Act: 2.2827. Min Act: -0.0000

Data Index: 211213 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 3.7079. Min Range: -3.7079

Max Act: 2.3223. Min Act: -0.0000

Data Index: 194324 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 3.7079. Min Range: -3.7079

Max Act: 2.0742. Min Act: -0.0000

Data Index: 1664495 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.9013. Min Act: -0.0000

Data Index: 135509 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1878105 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.8339. Min Act: -0.0000

Data Index: 882306 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.8347. Min Act: -0.0000

Data Index: 1181670 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.8163. Min Act: -0.0000

Data Index: 333173 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.7716. Min Act: -0.0000

Data Index: 833964 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.5650. Min Act: -0.0000

Data Index: 1400621 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1287755 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.5346. Min Act: -0.0000

Data Index: 874361 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.6135. Min Act: -0.0000

Data Index: 682061 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.7895. Min Act: -0.0000

Data Index: 956177 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.5220. Min Act: -0.0000

Data Index: 483190 (The Pile)

Max Activating Token Index: 563

Text #18

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.4990. Min Act: -0.0000

Data Index: 612847 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 3.7079. Min Range: -3.7079

Max Act: 1.4917. Min Act: -0.0000

Data Index: 113341 (The Pile)

Max Activating Token Index: 16