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

Dataset: The Pile

Neuron 2996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.8130. Min Act: -0.0000

Data Index: 708894 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1885853 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1353027 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7363. Min Act: -0.0000

Data Index: 715791 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1682152 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1179388 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.7409. Min Act: -0.0000

Data Index: 860864 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1452492 (The Pile)

Max Activating Token Index: 529

Text #8

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6200. Min Act: -0.0000

Data Index: 103795 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6868. Min Act: -0.0000

Data Index: 706350 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1984901 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6540. Min Act: -0.0000

Data Index: 573578 (The Pile)

Max Activating Token Index: 265

Text #12

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6414. Min Act: -0.0000

Data Index: 878035 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.5795. Min Act: -0.0000

Data Index: 559875 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1034012 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1863257 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.5788. Min Act: -0.0000

Data Index: 951948 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1406963 (The Pile)

Max Activating Token Index: 459

Text #18

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1933203 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 0.8521. Min Range: -0.8521

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1283903 (The Pile)

Max Activating Token Index: 351