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

Dataset: The Pile

Neuron 153 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3983. Min Range: -8.3983

Max Act: 8.3983. Min Act: -0.0000

Data Index: 613139 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 8.3983. Min Range: -8.3983

Max Act: 7.3655. Min Act: -0.0000

Data Index: 1347772 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 8.3983. Min Range: -8.3983

Max Act: 6.7767. Min Act: -0.0000

Data Index: 543984 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 8.3983. Min Range: -8.3983

Max Act: 6.8021. Min Act: -0.0000

Data Index: 798519 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 8.3983. Min Range: -8.3983

Max Act: 6.5611. Min Act: -0.0000

Data Index: 1775075 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 8.3983. Min Range: -8.3983

Max Act: 6.1978. Min Act: -0.0000

Data Index: 1522094 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 8.3983. Min Range: -8.3983

Max Act: 6.1917. Min Act: -0.0000

Data Index: 605960 (The Pile)

Max Activating Token Index: 612

Text #7

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.7421. Min Act: -0.0000

Data Index: 540651 (The Pile)

Max Activating Token Index: 819

Text #8

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.7361. Min Act: -0.0000

Data Index: 1626949 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.8492. Min Act: -0.0000

Data Index: 1557172 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 8.3983. Min Range: -8.3983

Max Act: 6.0491. Min Act: -0.0000

Data Index: 1745277 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.4863. Min Act: -0.0000

Data Index: 1487103 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 8.3983. Min Range: -8.3983

Max Act: 4.6374. Min Act: -0.0000

Data Index: 1461870 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.5861. Min Act: -0.0000

Data Index: 1339712 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.5020. Min Act: -0.0000

Data Index: 1986251 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.7029. Min Act: -0.0000

Data Index: 515815 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.4062. Min Act: -0.0000

Data Index: 1340022 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.5893. Min Act: -0.0000

Data Index: 1578284 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 8.3983. Min Range: -8.3983

Max Act: 5.5088. Min Act: -0.0000

Data Index: 459292 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 8.3983. Min Range: -8.3983

Max Act: 4.9825. Min Act: -0.0000

Data Index: 698147 (The Pile)

Max Activating Token Index: 403