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

Dataset: The Pile

Neuron 2451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1811691 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.9373. Min Act: -0.0000

Data Index: 465169 (The Pile)

Max Activating Token Index: 784

Text #2

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.9752. Min Act: -0.0000

Data Index: 431676 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8521. Min Act: -0.0000

Data Index: 743513 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.9521. Min Act: -0.0000

Data Index: 105786 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1272290 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1070344 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8570. Min Act: -0.0000

Data Index: 917896 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1373075 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7451. Min Act: -0.0000

Data Index: 470838 (The Pile)

Max Activating Token Index: 184

Text #10

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8405. Min Act: -0.0000

Data Index: 685809 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 1.0246. Min Range: -1.0246

Max Act: 1.0246. Min Act: -0.0000

Data Index: 943543 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8047. Min Act: -0.0000

Data Index: 899946 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1895385 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7453. Min Act: -0.0000

Data Index: 474097 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1499704 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1356410 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.6761. Min Act: -0.0000

Data Index: 135672 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7237. Min Act: -0.0000

Data Index: 732813 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.6587. Min Act: -0.0000

Data Index: 53572 (The Pile)

Max Activating Token Index: 170