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

Dataset: The Pile

Neuron 3167 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: 0.8414. Min Range: -0.8414

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1380631 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6533. Min Act: -0.0000

Data Index: 835163 (The Pile)

Max Activating Token Index: 891

Text #2

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6787. Min Act: -0.0000

Data Index: 488361 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1182689 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5671. Min Act: -0.0000

Data Index: 969097 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5833. Min Act: -0.0000

Data Index: 586769 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1561876 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1194843 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1037877 (The Pile)

Max Activating Token Index: 18

Text #9

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1868845 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1496644 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.4977. Min Act: -0.0000

Data Index: 132370 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1884295 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5039. Min Act: -0.0000

Data Index: 151255 (The Pile)

Max Activating Token Index: 136

Text #14

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1884746 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1789482 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1652803 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.4532. Min Act: -0.0000

Data Index: 439740 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1377163 (The Pile)

Max Activating Token Index: 83

Text #19

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1451453 (The Pile)

Max Activating Token Index: 45