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

Dataset: The Pile

Neuron 3952 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: 3.6728. Min Range: -3.6728

Max Act: 3.6143. Min Act: -0.0000

Data Index: 1860336 (The Pile)

Max Activating Token Index: 496

Text #1

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.4287. Min Act: 0.0000

Data Index: 767489 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.6728. Min Act: -0.0000

Data Index: 1517741 (The Pile)

Max Activating Token Index: 729

Text #3

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.1906. Min Act: -0.0000

Data Index: 612956 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.4527. Min Act: -0.0000

Data Index: 919040 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.4307. Min Act: -0.0000

Data Index: 1051021 (The Pile)

Max Activating Token Index: 74

Text #6

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.5893. Min Act: -0.0000

Data Index: 152817 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.4057. Min Act: -0.0000

Data Index: 1209333 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.3908. Min Act: -0.0000

Data Index: 1498727 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.3061. Min Act: -0.0000

Data Index: 788366 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.3185. Min Act: 0.0000

Data Index: 384685 (The Pile)

Max Activating Token Index: 880

Text #11

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.4365. Min Act: 0.0000

Data Index: 1402112 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.4079. Min Act: -0.0000

Data Index: 1095559 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.0335. Min Act: -0.0000

Data Index: 1613433 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.1485. Min Act: -0.0000

Data Index: 168196 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.2969. Min Act: -0.0000

Data Index: 1300404 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.0167. Min Act: -0.0000

Data Index: 1841085 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 3.6728. Min Range: -3.6728

Max Act: 2.9863. Min Act: -0.0000

Data Index: 1822849 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.2615. Min Act: -0.0000

Data Index: 775221 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 3.6728. Min Range: -3.6728

Max Act: 3.1577. Min Act: -0.0000

Data Index: 1298305 (The Pile)

Max Activating Token Index: 54