Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1449147 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1529385 (Python Code)

Max Activating Token Index: 938

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1093572 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1489462 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1377263 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0542. Min Act: -0.0002

Data Index: 148998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1649072 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0470. Min Act: -0.0002

Data Index: 142701 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1004838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0391. Min Act: -0.0002

Data Index: 358068 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0376. Min Act: -0.0002

Data Index: 668586 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1158310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0410. Min Act: -0.0002

Data Index: 742564 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0372. Min Act: -0.0002

Data Index: 897265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0349. Min Act: -0.0002

Data Index: 796033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1638256 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0363. Min Act: -0.0002

Data Index: 25749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0346. Min Act: -0.0002

Data Index: 862005 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0348. Min Act: -0.0002

Data Index: 369739 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1237706 (C4 (Web Text))

Max Activating Token Index: 1023