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

Dataset: The Pile

Neuron 4647 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: 0.6097. Min Range: -0.6097

Max Act: 0.6097. Min Act: -0.0000

Data Index: 638560 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1980239 (The Pile)

Max Activating Token Index: 811

Text #2

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1599862 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5504. Min Act: -0.0000

Data Index: 825229 (The Pile)

Max Activating Token Index: 877

Text #4

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5628. Min Act: -0.0000

Data Index: 656871 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1941733 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1615619 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1003928 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1091368 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5324. Min Act: -0.0000

Data Index: 556374 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5061. Min Act: -0.0000

Data Index: 356668 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5422. Min Act: -0.0000

Data Index: 841340 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1157577 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5172. Min Act: -0.0000

Data Index: 267686 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5009. Min Act: -0.0000

Data Index: 785739 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1619138 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5341. Min Act: -0.0000

Data Index: 729705 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1877920 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1374144 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.6097. Min Range: -0.6097

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1996246 (The Pile)

Max Activating Token Index: 481