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

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

Neuron 2247 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: 0.0857. Min Range: -0.0857

Max Act: 0.0857. Min Act: -0.0004

Data Index: 321876 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0528. Min Act: -0.0004

Data Index: 1346443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0468. Min Act: -0.0004

Data Index: 330658 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0470. Min Act: -0.0004

Data Index: 1296944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0486. Min Act: -0.0004

Data Index: 474452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0459. Min Act: -0.0004

Data Index: 1358189 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0479. Min Act: -0.0004

Data Index: 276642 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0385. Min Act: -0.0004

Data Index: 862995 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0354. Min Act: -0.0004

Data Index: 102443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0423. Min Act: -0.0004

Data Index: 901481 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0416. Min Act: -0.0004

Data Index: 1075023 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0422. Min Act: -0.0004

Data Index: 657144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0434. Min Act: -0.0004

Data Index: 384035 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0394. Min Act: -0.0004

Data Index: 85359 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0399. Min Act: -0.0004

Data Index: 676932 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0406. Min Act: -0.0004

Data Index: 128324 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0401. Min Act: -0.0004

Data Index: 1588142 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0385. Min Act: -0.0004

Data Index: 618247 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0386. Min Act: -0.0004

Data Index: 434019 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0387. Min Act: -0.0004

Data Index: 760352 (C4 (Web Text))

Max Activating Token Index: 1023