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

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

Neuron 4829 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5839. Min Act: -0.0000

Data Index: 689558 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.6061. Min Act: -0.0000

Data Index: 300585 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.5119. Min Act: -0.0000

Data Index: 115336 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4907. Min Act: -0.0000

Data Index: 158273 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.4430. Min Act: -0.0000

Data Index: 1228030 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1178801 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.2574. Min Act: -0.0000

Data Index: 248669 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.1624. Min Act: 0.0000

Data Index: 1336594 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.3617. Min Act: -0.0000

Data Index: 475170 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.1386. Min Act: -0.0000

Data Index: 81895 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.1835. Min Act: -0.0000

Data Index: 1301042 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.2381. Min Act: 0.0000

Data Index: 1106644 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.2218. Min Act: -0.0000

Data Index: 213269 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.1150. Min Act: -0.0000

Data Index: 622299 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0851. Min Act: -0.0000

Data Index: 323484 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.2117. Min Act: -0.0000

Data Index: 312091 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0659. Min Act: -0.0000

Data Index: 177800 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0690. Min Act: -0.0000

Data Index: 320804 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0481. Min Act: 0.0000

Data Index: 833434 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.6061. Min Range: -1.6061

Max Act: 1.0899. Min Act: -0.0000

Data Index: 838826 (C4 (Web Text))

Max Activating Token Index: 161