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

Dataset: The Pile

Neuron 3521 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: 1.0022. Min Range: -1.0022

Max Act: 0.9963. Min Act: -0.0000

Data Index: 942617 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.0022. Min Range: -1.0022

Max Act: 1.0022. Min Act: -0.0000

Data Index: 702301 (The Pile)

Max Activating Token Index: 471

Text #2

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1752747 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8408. Min Act: -0.0000

Data Index: 74752 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1831070 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1667120 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8442. Min Act: -0.0000

Data Index: 687371 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1780914 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1618125 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8547. Min Act: -0.0000

Data Index: 665763 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7781. Min Act: -0.0000

Data Index: 768633 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1369767 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1410880 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.8096. Min Act: -0.0000

Data Index: 297912 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7720. Min Act: -0.0000

Data Index: 363774 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1463552 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1206556 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7584. Min Act: -0.0000

Data Index: 156827 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1474372 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1919781 (The Pile)

Max Activating Token Index: 602