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

Dataset: The Pile

Neuron 1911 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: 0.9253. Min Range: -0.9253

Max Act: 0.9253. Min Act: -0.0000

Data Index: 564741 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.8147. Min Act: -0.0000

Data Index: 19018 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1015786 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1046545 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7648. Min Act: -0.0000

Data Index: 422930 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7370. Min Act: -0.0000

Data Index: 26858 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6708. Min Act: 0.0000

Data Index: 674090 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7582. Min Act: -0.0000

Data Index: 1437031 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1568702 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1060333 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1502721 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6501. Min Act: -0.0000

Data Index: 976749 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1360516 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1367812 (The Pile)

Max Activating Token Index: 236

Text #14

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1366150 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1251417 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6618. Min Act: -0.0000

Data Index: 835901 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6495. Min Act: -0.0000

Data Index: 216795 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6446. Min Act: 0.0000

Data Index: 1787749 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 0.9253. Min Range: -0.9253

Max Act: 0.6171. Min Act: -0.0000

Data Index: 909502 (The Pile)

Max Activating Token Index: 660