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

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

Neuron 1569 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: 1.1753. Min Range: -1.1753

Max Act: 1.1753. Min Act: -0.0000

Data Index: 803142 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.1476. Min Act: -0.0000

Data Index: 190860 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.1129. Min Act: -0.0000

Data Index: 892330 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9842. Min Act: -0.0000

Data Index: 733236 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9755. Min Act: -0.0000

Data Index: 137816 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1062943 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9696. Min Act: -0.0000

Data Index: 915303 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9983. Min Act: -0.0000

Data Index: 14026 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1298145 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9568. Min Act: -0.0000

Data Index: 628435 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1212059 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9335. Min Act: -0.0000

Data Index: 28544 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9035. Min Act: -0.0000

Data Index: 122848 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1387051 (Python Code)

Max Activating Token Index: 184

Text #14

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9576. Min Act: -0.0000

Data Index: 30659 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9491. Min Act: -0.0000

Data Index: 79135 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9350. Min Act: -0.0000

Data Index: 313204 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1348032 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1333793 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8231. Min Act: -0.0000

Data Index: 497005 (C4 (Web Text))

Max Activating Token Index: 856