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

Dataset: The Pile

Neuron 1615 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: 1.9613. Min Range: -1.9613

Max Act: 1.9613. Min Act: -0.0000

Data Index: 128171 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.9002. Min Act: -0.0000

Data Index: 1248117 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1172036 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.6182. Min Act: -0.0000

Data Index: 839509 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7565. Min Act: -0.0000

Data Index: 485691 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.6116. Min Act: -0.0000

Data Index: 591470 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.5540. Min Act: -0.0000

Data Index: 898666 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.6650. Min Act: -0.0000

Data Index: 1199714 (The Pile)

Max Activating Token Index: 703

Text #8

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.5378. Min Act: -0.0000

Data Index: 59704 (The Pile)

Max Activating Token Index: 485

Text #9

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.5699. Min Act: -0.0000

Data Index: 1958948 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1708022 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1471812 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1087781 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1145183 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4378. Min Act: -0.0000

Data Index: 560522 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1565414 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4323. Min Act: -0.0000

Data Index: 1793152 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4504. Min Act: -0.0000

Data Index: 1304269 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4522. Min Act: -0.0000

Data Index: 227586 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1753672 (The Pile)

Max Activating Token Index: 671