Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3962 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1457651 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1068473 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0509. Min Act: -0.0000

Data Index: 59085 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.1700. Min Range: -1.1700

Max Act: 1.0680. Min Act: -0.0000

Data Index: 402988 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9876. Min Act: -0.0000

Data Index: 903305 (The Pile)

Max Activating Token Index: 819

Text #5

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1003095 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9657. Min Act: -0.0000

Data Index: 751473 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1333356 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1023398 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1920670 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.7810. Min Act: -0.0000

Data Index: 349864 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1924058 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1698011 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1777195 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.7954. Min Act: -0.0000

Data Index: 761847 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1031301 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1374722 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.7926. Min Act: -0.0000

Data Index: 152274 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.7821. Min Act: -0.0000

Data Index: 495301 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 1.1700. Min Range: -1.1700

Max Act: 0.7670. Min Act: -0.0000

Data Index: 393163 (The Pile)

Max Activating Token Index: 625