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

Dataset: The Pile

Neuron 1001 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: 3.0206. Min Range: -3.0206

Max Act: 3.0206. Min Act: -0.0000

Data Index: 139024 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 3.0206. Min Range: -3.0206

Max Act: 2.4552. Min Act: -0.0000

Data Index: 85510 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 3.0206. Min Range: -3.0206

Max Act: 2.2069. Min Act: -0.0000

Data Index: 390107 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.8551. Min Act: -0.0000

Data Index: 1766950 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.8698. Min Act: -0.0000

Data Index: 624578 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.9381. Min Act: -0.0000

Data Index: 62486 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6493. Min Act: -0.0000

Data Index: 159038 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.8365. Min Act: -0.0000

Data Index: 1908300 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.7815. Min Act: -0.0000

Data Index: 894070 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.8800. Min Act: -0.0000

Data Index: 1453180 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6577. Min Act: -0.0000

Data Index: 1097453 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.7290. Min Act: -0.0000

Data Index: 1508302 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.7362. Min Act: -0.0000

Data Index: 580188 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6083. Min Act: -0.0000

Data Index: 59409 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6587. Min Act: -0.0000

Data Index: 226388 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6818. Min Act: -0.0000

Data Index: 1204156 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6613. Min Act: -0.0000

Data Index: 730104 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6308. Min Act: -0.0000

Data Index: 673804 (The Pile)

Max Activating Token Index: 915

Text #18

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6370. Min Act: -0.0000

Data Index: 1952170 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1969326 (The Pile)

Max Activating Token Index: 556