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

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

Neuron 1828 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: 3.4528. Min Range: -3.4528

Max Act: 3.4528. Min Act: -0.0001

Data Index: 831282 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 3.4528. Min Range: -3.4528

Max Act: 3.4270. Min Act: -0.0001

Data Index: 436222 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 3.4528. Min Range: -3.4528

Max Act: 2.3397. Min Act: -0.0000

Data Index: 1143852 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 3.4528. Min Range: -3.4528

Max Act: 2.4225. Min Act: -0.0000

Data Index: 961865 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 3.4528. Min Range: -3.4528

Max Act: 2.2530. Min Act: -0.0000

Data Index: 922442 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 3.4528. Min Range: -3.4528

Max Act: 2.2027. Min Act: -0.0001

Data Index: 62051 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.4528. Min Range: -3.4528

Max Act: 2.0494. Min Act: -0.0000

Data Index: 761910 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 3.4528. Min Range: -3.4528

Max Act: 2.1552. Min Act: -0.0000

Data Index: 532450 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.9286. Min Act: -0.0001

Data Index: 310026 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.9068. Min Act: -0.0000

Data Index: 1220980 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.8995. Min Act: -0.0000

Data Index: 309653 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.9831. Min Act: -0.0001

Data Index: 788761 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.9672. Min Act: -0.0000

Data Index: 1246795 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.9533. Min Act: -0.0000

Data Index: 426214 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.9449. Min Act: -0.0000

Data Index: 406604 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.9185. Min Act: -0.0001

Data Index: 265630 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.9044. Min Act: -0.0000

Data Index: 1098861 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.7983. Min Act: -0.0001

Data Index: 1228246 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.8803. Min Act: -0.0001

Data Index: 82193 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 3.4528. Min Range: -3.4528

Max Act: 1.8629. Min Act: -0.0001

Data Index: 790047 (C4 (Web Text))

Max Activating Token Index: 53