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

Dataset: The Pile

Neuron 2198 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0191. Min Range: -5.0191

Max Act: 5.0191. Min Act: 0.0000

Data Index: 881610 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.7006. Min Act: -0.0000

Data Index: 1011420 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.2932. Min Act: -0.0000

Data Index: 1312686 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.1035. Min Act: -0.0000

Data Index: 1867489 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.0606. Min Act: -0.0000

Data Index: 983912 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.0337. Min Act: -0.0000

Data Index: 195894 (The Pile)

Max Activating Token Index: 625

Text #6

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.1855. Min Act: -0.0000

Data Index: 596148 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.1703. Min Act: -0.0000

Data Index: 857343 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.9801. Min Act: -0.0000

Data Index: 1027781 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.0023. Min Act: -0.0000

Data Index: 1052611 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.9607. Min Act: 0.0000

Data Index: 827422 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.0858. Min Act: -0.0000

Data Index: 1878912 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 5.0191. Min Range: -5.0191

Max Act: 4.1068. Min Act: -0.0000

Data Index: 1665652 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.9365. Min Act: -0.0000

Data Index: 1894686 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.9285. Min Act: -0.0000

Data Index: 1735018 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.9299. Min Act: -0.0000

Data Index: 1107644 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.8762. Min Act: -0.0000

Data Index: 252935 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.8969. Min Act: -0.0000

Data Index: 1891583 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.8478. Min Act: -0.0000

Data Index: 74066 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 5.0191. Min Range: -5.0191

Max Act: 3.7764. Min Act: -0.0000

Data Index: 1299051 (The Pile)

Max Activating Token Index: 1001