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

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

Neuron 1400 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: 1.0084. Min Range: -1.0084

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1122093 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.9144. Min Act: -0.0000

Data Index: 396149 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.8837. Min Act: -0.0000

Data Index: 598158 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.8733. Min Act: -0.0000

Data Index: 706530 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.8621. Min Act: -0.0000

Data Index: 965887 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.9284. Min Act: -0.0000

Data Index: 619456 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.8533. Min Act: -0.0000

Data Index: 456351 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1034242 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.7904. Min Act: -0.0000

Data Index: 582363 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.7728. Min Act: -0.0000

Data Index: 814210 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.8396. Min Act: -0.0000

Data Index: 246558 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.7623. Min Act: -0.0000

Data Index: 29502 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.7311. Min Act: -0.0000

Data Index: 84254 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.7629. Min Act: -0.0000

Data Index: 550954 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1090051 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.7106. Min Act: -0.0000

Data Index: 967576 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1088402 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.6763. Min Act: -0.0000

Data Index: 303368 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.8090. Min Act: -0.0000

Data Index: 367739 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 1.0084. Min Range: -1.0084

Max Act: 0.6750. Min Act: -0.0000

Data Index: 685758 (C4 (Web Text))

Max Activating Token Index: 871