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

Dataset: The Pile

Neuron 250 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: 1.5933. Min Range: -1.5933

Max Act: 1.5874. Min Act: -0.0000

Data Index: 280681 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5861. Min Act: -0.0000

Data Index: 761091 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5933. Min Act: -0.0000

Data Index: 317868 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5234. Min Act: -0.0000

Data Index: 983823 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5058. Min Act: -0.0000

Data Index: 1275694 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.3998. Min Act: -0.0000

Data Index: 1445802 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.3120. Min Act: -0.0000

Data Index: 342910 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1954. Min Act: -0.0000

Data Index: 1090390 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2313. Min Act: -0.0000

Data Index: 632571 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1496. Min Act: -0.0000

Data Index: 1159275 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1254. Min Act: -0.0000

Data Index: 100253 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2561. Min Act: -0.0000

Data Index: 737684 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1797. Min Act: -0.0000

Data Index: 952870 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1203012 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1695. Min Act: -0.0000

Data Index: 280837 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1685. Min Act: -0.0000

Data Index: 1532705 (The Pile)

Max Activating Token Index: 912

Text #16

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1692. Min Act: -0.0000

Data Index: 878874 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1065355 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1568. Min Act: -0.0000

Data Index: 396183 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1764960 (The Pile)

Max Activating Token Index: 917