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

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

Neuron 4043 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: 1.1388. Min Range: -1.1388

Max Act: 1.1388. Min Act: -0.0000

Data Index: 982798 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.1388. Min Range: -1.1388

Max Act: 1.0917. Min Act: -0.0000

Data Index: 949097 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.1388. Min Range: -1.1388

Max Act: 1.0412. Min Act: -0.0000

Data Index: 115495 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.1388. Min Range: -1.1388

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1247817 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.9337. Min Act: -0.0001

Data Index: 1087643 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.9459. Min Act: -0.0001

Data Index: 578790 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1156347 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.9682. Min Act: -0.0001

Data Index: 432387 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1150921 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.9160. Min Act: -0.0001

Data Index: 672639 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.8997. Min Act: -0.0001

Data Index: 1204891 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.8677. Min Act: -0.0001

Data Index: 859739 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.8583. Min Act: -0.0001

Data Index: 612419 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.8312. Min Act: -0.0000

Data Index: 898126 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.8072. Min Act: -0.0001

Data Index: 790885 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.7943. Min Act: -0.0000

Data Index: 160335 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.8004. Min Act: -0.0000

Data Index: 589997 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.7788. Min Act: -0.0000

Data Index: 671453 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1323275 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.1388. Min Range: -1.1388

Max Act: 0.7992. Min Act: -0.0001

Data Index: 426439 (C4 (Web Text))

Max Activating Token Index: 596