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

Dataset: The Pile

Neuron 2198 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: 1.9802. Min Range: -1.9802

Max Act: 1.9802. Min Act: -0.0000

Data Index: 1157553 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 1.9802. Min Range: -1.9802

Max Act: 1.0623. Min Act: -0.0000

Data Index: 748133 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.9988. Min Act: -0.0000

Data Index: 737634 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.9218. Min Act: -0.0000

Data Index: 604761 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.9099. Min Act: -0.0000

Data Index: 1980177 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1807279 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.8870. Min Act: -0.0000

Data Index: 112993 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1382753 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1854345 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1874134 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1383386 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7362. Min Act: -0.0000

Data Index: 370841 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1423965 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1702372 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1881389 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1743979 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7896. Min Act: -0.0000

Data Index: 3457 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1935966 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1730642 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 1.9802. Min Range: -1.9802

Max Act: 0.7385. Min Act: -0.0000

Data Index: 33842 (The Pile)

Max Activating Token Index: 472