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

Dataset: The Pile

Neuron 3108 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.7236. Min Act: 0.0000

Data Index: 457007 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.7015. Min Act: -0.0000

Data Index: 1918052 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1782657 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1550. Min Act: -0.0000

Data Index: 191594 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1019692 (The Pile)

Max Activating Token Index: 339

Text #5

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1876. Min Act: -0.0000

Data Index: 760334 (The Pile)

Max Activating Token Index: 753

Text #6

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1038363 (The Pile)

Max Activating Token Index: 969

Text #7

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1107. Min Act: -0.0000

Data Index: 1554516 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1653076 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.0981. Min Act: -0.0000

Data Index: 376333 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.0038. Min Act: -0.0000

Data Index: 375313 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1586771 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 1.7236. Min Range: -1.7236

Max Act: 0.9581. Min Act: -0.0000

Data Index: 762423 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 1.7236. Min Range: -1.7236

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1010829 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 1.7236. Min Range: -1.7236

Max Act: 1.0560. Min Act: -0.0000

Data Index: 629355 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 1.7236. Min Range: -1.7236

Max Act: 0.9428. Min Act: -0.0000

Data Index: 752815 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 1.7236. Min Range: -1.7236

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1486332 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 1.7236. Min Range: -1.7236

Max Act: 0.9068. Min Act: -0.0000

Data Index: 317855 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 1.7236. Min Range: -1.7236

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1274163 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 1.7236. Min Range: -1.7236

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1027948 (The Pile)

Max Activating Token Index: 786