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

Dataset: The Pile

Neuron 2345 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.7449. Min Act: -0.0000

Data Index: 1924628 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.3718. Min Act: -0.0000

Data Index: 333796 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.1403. Min Act: -0.0000

Data Index: 848941 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1880274 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1959009 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.0871. Min Act: -0.0000

Data Index: 1328882 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.0402. Min Act: -0.0000

Data Index: 212092 (The Pile)

Max Activating Token Index: 846

Text #7

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1472043 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1414967 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 1.7449. Min Range: -1.7449

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1074262 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.0048. Min Act: -0.0000

Data Index: 812770 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 1.7449. Min Range: -1.7449

Max Act: 0.9443. Min Act: -0.0000

Data Index: 360270 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.0018. Min Act: -0.0000

Data Index: 721290 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 1.7449. Min Range: -1.7449

Max Act: 0.9836. Min Act: -0.0000

Data Index: 938054 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.7449. Min Range: -1.7449

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1621451 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 1.7449. Min Range: -1.7449

Max Act: 0.9701. Min Act: -0.0000

Data Index: 240659 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 1.7449. Min Range: -1.7449

Max Act: 1.0206. Min Act: -0.0000

Data Index: 378849 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.7449. Min Range: -1.7449

Max Act: 0.9139. Min Act: -0.0000

Data Index: 164583 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 1.7449. Min Range: -1.7449

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1220205 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 1.7449. Min Range: -1.7449

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1193600 (The Pile)

Max Activating Token Index: 8