Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2798 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0573. Min Act: -0.0004

Data Index: 513866 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0504. Min Act: -0.0004

Data Index: 299736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0585. Min Act: -0.0004

Data Index: 242978 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0536. Min Act: -0.0004

Data Index: 1134227 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0530. Min Act: -0.0004

Data Index: 727631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0573. Min Act: -0.0004

Data Index: 955977 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0532. Min Act: -0.0004

Data Index: 1055034 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0529. Min Act: -0.0004

Data Index: 1284412 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0502. Min Act: -0.0004

Data Index: 569522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0495. Min Act: -0.0004

Data Index: 325792 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0475. Min Act: -0.0004

Data Index: 668653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0473. Min Act: -0.0004

Data Index: 1264351 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0475. Min Act: -0.0004

Data Index: 975882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0472. Min Act: -0.0004

Data Index: 983409 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0467. Min Act: -0.0004

Data Index: 499047 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0483. Min Act: -0.0004

Data Index: 1297018 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0477. Min Act: -0.0004

Data Index: 1398830 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0480. Min Act: -0.0004

Data Index: 645884 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0471. Min Act: -0.0004

Data Index: 526454 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0454. Min Act: -0.0004

Data Index: 280708 (C4 (Web Text))

Max Activating Token Index: 1023