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

Dataset: The Pile

Neuron 224 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.3647. Min Act: -0.0000

Data Index: 1212303 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1918159 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1251005 (The Pile)

Max Activating Token Index: 956

Text #3

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1113197 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8979. Min Act: -0.0000

Data Index: 46758 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1469999 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1197697 (The Pile)

Max Activating Token Index: 558

Text #7

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1331989 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8681. Min Act: -0.0000

Data Index: 642661 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1536329 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7926. Min Act: -0.0000

Data Index: 885959 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8067. Min Act: -0.0000

Data Index: 566646 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8515. Min Act: -0.0000

Data Index: 717948 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8640. Min Act: -0.0000

Data Index: 54329 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1512040 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1599694 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1213794 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1934253 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1774201 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8277. Min Act: -0.0000

Data Index: 30250 (The Pile)

Max Activating Token Index: 809