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

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

Neuron 3814 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.6530. Min Act: -0.0000

Data Index: 480823 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.6457. Min Act: -0.0000

Data Index: 227956 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.5228. Min Act: -0.0000

Data Index: 594402 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4829. Min Act: -0.0000

Data Index: 330894 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4679. Min Act: -0.0000

Data Index: 313751 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4601. Min Act: -0.0000

Data Index: 956008 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4273. Min Act: -0.0000

Data Index: 677590 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1174752 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1311643 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4400. Min Act: -0.0000

Data Index: 860411 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4533. Min Act: -0.0000

Data Index: 163978 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4832. Min Act: -0.0000

Data Index: 719929 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1122395 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.3940. Min Act: -0.0000

Data Index: 887843 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4516. Min Act: -0.0000

Data Index: 973840 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4397. Min Act: -0.0000

Data Index: 389297 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4489. Min Act: -0.0000

Data Index: 849309 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1306977 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4467. Min Act: -0.0000

Data Index: 581991 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.6530. Min Range: -0.6530

Max Act: 0.4220. Min Act: -0.0000

Data Index: 99829 (C4 (Web Text))

Max Activating Token Index: 913