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

Dataset: The Pile

Neuron 508 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: 3.6365. Min Range: -3.6365

Max Act: 3.4595. Min Act: -0.0000

Data Index: 746797 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.6365. Min Act: -0.0000

Data Index: 677260 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.2323. Min Act: -0.0000

Data Index: 1474896 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.1507. Min Act: -0.0000

Data Index: 1217445 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4426. Min Act: -0.0000

Data Index: 288577 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.8489. Min Act: -0.0000

Data Index: 1070681 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.9621. Min Act: -0.0000

Data Index: 1410041 (The Pile)

Max Activating Token Index: 597

Text #7

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.0321. Min Act: -0.0000

Data Index: 1419291 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.0219. Min Act: -0.0000

Data Index: 1465762 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.0006. Min Act: -0.0000

Data Index: 1546118 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.9068. Min Act: -0.0000

Data Index: 1050628 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.8886. Min Act: -0.0000

Data Index: 1438227 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.9003. Min Act: -0.0000

Data Index: 1075725 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.8972. Min Act: -0.0000

Data Index: 1883556 (The Pile)

Max Activating Token Index: 383

Text #14

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.8766. Min Act: -0.0000

Data Index: 641280 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.8669. Min Act: -0.0000

Data Index: 686893 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.8548. Min Act: -0.0000

Data Index: 712613 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.8575. Min Act: -0.0000

Data Index: 214877 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.9969. Min Act: -0.0000

Data Index: 1088356 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 3.6365. Min Range: -3.6365

Max Act: 2.9800. Min Act: -0.0000

Data Index: 1555296 (The Pile)

Max Activating Token Index: 50