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

Dataset: The Pile

Neuron 1734 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: 0.6743. Min Range: -0.6743

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1788338 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1839711 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6380. Min Act: -0.0000

Data Index: 693884 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5820. Min Act: -0.0000

Data Index: 269170 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.6007. Min Act: -0.0000

Data Index: 148270 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5752. Min Act: -0.0000

Data Index: 142254 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1138306 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1318960 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1574900 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1086239 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1679457 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5461. Min Act: -0.0000

Data Index: 338796 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1163939 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5233. Min Act: -0.0000

Data Index: 714202 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5654. Min Act: -0.0000

Data Index: 375595 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1514021 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1158883 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5154. Min Act: -0.0000

Data Index: 138528 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1222831 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 0.6743. Min Range: -0.6743

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1006791 (The Pile)

Max Activating Token Index: 840