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

Dataset: The Pile

Neuron 1057 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: 3.6993. Min Range: -3.6993

Max Act: 3.6993. Min Act: -0.0000

Data Index: 1917791 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 3.6993. Min Range: -3.6993

Max Act: 3.4736. Min Act: -0.0000

Data Index: 1080242 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 3.6993. Min Range: -3.6993

Max Act: 3.0598. Min Act: -0.0000

Data Index: 618218 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 3.6993. Min Range: -3.6993

Max Act: 3.6451. Min Act: -0.0000

Data Index: 1654307 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 3.6993. Min Range: -3.6993

Max Act: 3.1206. Min Act: -0.0000

Data Index: 1161116 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 3.6993. Min Range: -3.6993

Max Act: 3.0493. Min Act: -0.0000

Data Index: 1150760 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.9771. Min Act: -0.0000

Data Index: 955295 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.6446. Min Act: -0.0000

Data Index: 918051 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.7487. Min Act: -0.0000

Data Index: 1339741 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.8673. Min Act: -0.0000

Data Index: 842544 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.7252. Min Act: -0.0000

Data Index: 1136928 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.9924. Min Act: -0.0000

Data Index: 1120711 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.8144. Min Act: -0.0000

Data Index: 1612418 (The Pile)

Max Activating Token Index: 206

Text #13

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.6393. Min Act: -0.0000

Data Index: 1428168 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.4923. Min Act: -0.0000

Data Index: 579542 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.6158. Min Act: -0.0000

Data Index: 1347064 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.7973. Min Act: -0.0000

Data Index: 1120922 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.6643. Min Act: -0.0000

Data Index: 344176 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.5262. Min Act: -0.0000

Data Index: 1342892 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 3.6993. Min Range: -3.6993

Max Act: 2.5127. Min Act: -0.0000

Data Index: 1616450 (The Pile)

Max Activating Token Index: 257