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

Dataset: The Pile

Neuron 2010 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: 0.6667. Min Range: -0.6667

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1411407 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5860. Min Act: -0.0000

Data Index: 574497 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1583881 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5633. Min Act: -0.0000

Data Index: 25847 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1133013 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1521966 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1406925 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1008466 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5190. Min Act: -0.0000

Data Index: 787198 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4644. Min Act: -0.0000

Data Index: 686203 (The Pile)

Max Activating Token Index: 787

Text #10

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4935. Min Act: -0.0000

Data Index: 701547 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1306763 (The Pile)

Max Activating Token Index: 47

Text #12

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4786. Min Act: -0.0000

Data Index: 274251 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5018. Min Act: -0.0000

Data Index: 569104 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4777. Min Act: -0.0000

Data Index: 506805 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4598. Min Act: -0.0000

Data Index: 208330 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5342. Min Act: -0.0000

Data Index: 247058 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1674275 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4390. Min Act: -0.0000

Data Index: 246476 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1864879 (The Pile)

Max Activating Token Index: 78