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

Dataset: The Pile

Neuron 4075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3818. Min Act: 0.0000

Data Index: 1721637 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1939369 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1891679 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3849. Min Act: -0.0000

Data Index: 694610 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1284889 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1577678 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3471. Min Act: -0.0000

Data Index: 870135 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3504. Min Act: -0.0000

Data Index: 437163 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1830290 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3561. Min Act: 0.0000

Data Index: 1717242 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3469. Min Act: -0.0000

Data Index: 868434 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3243. Min Act: 0.0000

Data Index: 1586602 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3104. Min Act: 0.0000

Data Index: 1968312 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3085. Min Act: 0.0000

Data Index: 1645119 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3215. Min Act: -0.0000

Data Index: 96540 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3013. Min Act: -0.0000

Data Index: 446337 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3160. Min Act: -0.0000

Data Index: 318961 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3066. Min Act: 0.0000

Data Index: 1892346 (The Pile)

Max Activating Token Index: 902

Text #18

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3112. Min Act: -0.0000

Data Index: 909361 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.3875. Min Range: -0.3875

Max Act: 0.3006. Min Act: -0.0000

Data Index: 1079299 (The Pile)

Max Activating Token Index: 610