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

Dataset: The Pile

Neuron 2350 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3595. Min Range: -6.3595

Max Act: 6.3595. Min Act: -0.0000

Data Index: 511488 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 6.3595. Min Range: -6.3595

Max Act: 6.1096. Min Act: -0.0000

Data Index: 323163 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 6.3595. Min Range: -6.3595

Max Act: 6.2749. Min Act: -0.0000

Data Index: 913141 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 6.3595. Min Range: -6.3595

Max Act: 6.0710. Min Act: -0.0000

Data Index: 684827 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.9087. Min Act: -0.0000

Data Index: 297977 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.5765. Min Act: -0.0000

Data Index: 674566 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.4780. Min Act: -0.0000

Data Index: 1544717 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.4463. Min Act: -0.0000

Data Index: 1945257 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.6081. Min Act: -0.0000

Data Index: 602437 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.5692. Min Act: -0.0000

Data Index: 258487 (The Pile)

Max Activating Token Index: 165

Text #10

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.7575. Min Act: -0.0000

Data Index: 227314 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.7095. Min Act: -0.0000

Data Index: 1969704 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.4949. Min Act: -0.0000

Data Index: 1263395 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.7088. Min Act: -0.0000

Data Index: 684331 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.6325. Min Act: -0.0000

Data Index: 1022869 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.2968. Min Act: -0.0000

Data Index: 1104720 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.4207. Min Act: -0.0000

Data Index: 1905292 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.3760. Min Act: -0.0000

Data Index: 1187736 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.5349. Min Act: -0.0000

Data Index: 893431 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 6.3595. Min Range: -6.3595

Max Act: 5.5113. Min Act: -0.0000

Data Index: 1471984 (The Pile)

Max Activating Token Index: 633