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

Dataset: The Pile

Neuron 1339 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: 0.9399. Min Range: -0.9399

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1170973 (The Pile)

Max Activating Token Index: 354

Text #1

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1237075 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1485968 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1833543 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1771326 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1664634 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.7545. Min Act: -0.0000

Data Index: 191672 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1966908 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1597636 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1994457 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1628532 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1482997 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.6530. Min Act: -0.0000

Data Index: 776477 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1061280 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1791049 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1521626 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5665. Min Act: -0.0000

Data Index: 264948 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5887. Min Act: -0.0000

Data Index: 418716 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.6206. Min Act: -0.0000

Data Index: 269961 (The Pile)

Max Activating Token Index: 513

Text #19

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1179572 (The Pile)

Max Activating Token Index: 881