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

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

Neuron 233 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.7620. Min Act: -0.0000

Data Index: 386037 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1164912 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1353346 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5746. Min Act: -0.0000

Data Index: 818701 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5893. Min Act: -0.0000

Data Index: 680111 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5299. Min Act: -0.0000

Data Index: 598364 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5602. Min Act: -0.0000

Data Index: 597149 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1201812 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5318. Min Act: -0.0000

Data Index: 774946 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5294. Min Act: -0.0000

Data Index: 10434 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5550. Min Act: -0.0000

Data Index: 787101 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5184. Min Act: -0.0000

Data Index: 189215 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5128. Min Act: -0.0000

Data Index: 113497 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4895. Min Act: -0.0000

Data Index: 856780 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5214. Min Act: -0.0000

Data Index: 713602 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5145. Min Act: -0.0000

Data Index: 928916 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4876. Min Act: -0.0000

Data Index: 245540 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1174614 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1025353 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.7620. Min Range: -0.7620

Max Act: 0.4979. Min Act: -0.0000

Data Index: 474767 (C4 (Web Text))

Max Activating Token Index: 113