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

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

Neuron 558 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0479. Min Range: -2.0479

Max Act: 2.0479. Min Act: -0.0000

Data Index: 1285859 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 2.0479. Min Range: -2.0479

Max Act: 1.7468. Min Act: -0.0000

Data Index: 904530 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.8035. Min Act: -0.0000

Data Index: 376269 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.8819. Min Act: -0.0000

Data Index: 318642 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1238113 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7454. Min Act: -0.0000

Data Index: 115069 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.8992. Min Act: -0.0000

Data Index: 1112385 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7424. Min Act: -0.0000

Data Index: 27668 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7421. Min Act: -0.0000

Data Index: 660224 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7114. Min Act: -0.0000

Data Index: 897399 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1025555 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.6808. Min Act: -0.0000

Data Index: 845476 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7571. Min Act: -0.0000

Data Index: 746916 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.8037. Min Act: -0.0000

Data Index: 678024 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7433. Min Act: -0.0000

Data Index: 535058 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7811. Min Act: -0.0000

Data Index: 477794 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7543. Min Act: -0.0000

Data Index: 828167 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1205620 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7223. Min Act: -0.0000

Data Index: 197132 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.0479. Min Range: -2.0479

Max Act: 0.7203. Min Act: -0.0000

Data Index: 525535 (C4 (Web Text))

Max Activating Token Index: 195