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

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

Neuron 192 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.9854. Min Act: -0.0000

Data Index: 688730 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.8787. Min Act: -0.0000

Data Index: 573055 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1219723 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.8502. Min Act: -0.0000

Data Index: 817296 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7919. Min Act: -0.0001

Data Index: 461009 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1067873 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7474. Min Act: -0.0000

Data Index: 532175 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7185. Min Act: -0.0000

Data Index: 969209 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7886. Min Act: -0.0001

Data Index: 1224835 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7595. Min Act: -0.0000

Data Index: 135895 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7374. Min Act: -0.0000

Data Index: 757147 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7559. Min Act: -0.0001

Data Index: 1072890 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7748. Min Act: -0.0001

Data Index: 526487 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7276. Min Act: -0.0001

Data Index: 553628 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1354456 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7687. Min Act: -0.0001

Data Index: 487378 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.6951. Min Act: -0.0000

Data Index: 379688 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7372. Min Act: -0.0000

Data Index: 675760 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.6848. Min Act: -0.0001

Data Index: 469102 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.9854. Min Range: -0.9854

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1354388 (C4 (Web Text))

Max Activating Token Index: 889