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

Dataset: The Pile

Neuron 2007 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: 1.3456. Min Range: -1.3456

Max Act: 1.3110. Min Act: -0.0000

Data Index: 147316 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.2115. Min Act: -0.0000

Data Index: 93600 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1685555 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.2181. Min Act: -0.0000

Data Index: 537514 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.1159. Min Act: -0.0000

Data Index: 963345 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.1488. Min Act: -0.0000

Data Index: 265825 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.1540. Min Act: -0.0000

Data Index: 993700 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1492292 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.0587. Min Act: -0.0000

Data Index: 953038 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1453087 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.0438. Min Act: -0.0000

Data Index: 704862 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.0924. Min Act: -0.0000

Data Index: 830547 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1287784 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.3456. Min Range: -1.3456

Max Act: 0.9896. Min Act: -0.0000

Data Index: 632799 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.0393. Min Act: -0.0000

Data Index: 860958 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.0312. Min Act: -0.0000

Data Index: 547853 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 1.3456. Min Range: -1.3456

Max Act: 0.9793. Min Act: -0.0000

Data Index: 721304 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 1.3456. Min Range: -1.3456

Max Act: 0.9315. Min Act: -0.0000

Data Index: 377069 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.0113. Min Act: -0.0000

Data Index: 397301 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 1.3456. Min Range: -1.3456

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1042562 (The Pile)

Max Activating Token Index: 191