Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1064 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.3147. Min Act: -0.0000

Data Index: 496839 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0289. Min Act: -0.0000

Data Index: 435481 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1194898 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1311615 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.8560. Min Act: -0.0000

Data Index: 721168 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.8359. Min Act: -0.0000

Data Index: 531632 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.7566. Min Act: -0.0000

Data Index: 491179 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6912. Min Act: -0.0000

Data Index: 474475 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.7241. Min Act: -0.0000

Data Index: 528755 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.7028. Min Act: -0.0000

Data Index: 514313 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.7029. Min Act: -0.0000

Data Index: 252798 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.7662. Min Act: -0.0000

Data Index: 694866 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6394. Min Act: -0.0000

Data Index: 518016 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1331829 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1312169 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1066773 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6544. Min Act: -0.0000

Data Index: 997777 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6483. Min Act: -0.0000

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.6518. Min Act: -0.0000

Data Index: 497718 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.3147. Min Range: -1.3147

Max Act: 0.5815. Min Act: -0.0000

Data Index: 999835 (C4 (Web Text))

Max Activating Token Index: 354