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

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

Neuron 2173 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.8467. Min Act: -0.0000

Data Index: 149652 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.4920. Min Act: -0.0000

Data Index: 900202 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.6934. Min Act: -0.0001

Data Index: 794134 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3819. Min Act: -0.0000

Data Index: 805650 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.1494. Min Act: -0.0000

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.9720. Min Act: -0.0001

Data Index: 145636 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.7595. Min Act: -0.0001

Data Index: 1324375 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.8084. Min Act: -0.0000

Data Index: 38070 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.6461. Min Act: -0.0000

Data Index: 483317 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.8217. Min Act: -0.0001

Data Index: 1096955 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.8282. Min Act: -0.0000

Data Index: 1046064 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.5477. Min Act: -0.0000

Data Index: 509319 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 4.8467. Min Range: -4.8467

Max Act: 4.3781. Min Act: -0.0001

Data Index: 423295 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.2397. Min Act: -0.0001

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.0667. Min Act: -0.0000

Data Index: 1260994 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.3072. Min Act: -0.0000

Data Index: 197794 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.7245. Min Act: -0.0000

Data Index: 119231 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.2523. Min Act: -0.0000

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.3658. Min Act: -0.0001

Data Index: 422523 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 4.8467. Min Range: -4.8467

Max Act: 3.6327. Min Act: -0.0000

Data Index: 1042404 (C4 (Web Text))

Max Activating Token Index: 1022