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

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

Neuron 1109 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: 5.4439. Min Range: -5.4439

Max Act: 4.3867. Min Act: -0.0000

Data Index: 372688 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 5.4439. Min Range: -5.4439

Max Act: 5.4439. Min Act: -0.0000

Data Index: 970169 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.6129. Min Act: -0.0000

Data Index: 1170074 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.7451. Min Act: -0.0000

Data Index: 1158024 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.3810. Min Act: -0.0000

Data Index: 969587 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.6599. Min Act: -0.0000

Data Index: 301395 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.2359. Min Act: -0.0000

Data Index: 48132 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.1588. Min Act: -0.0000

Data Index: 1263458 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.1727. Min Act: -0.0000

Data Index: 1049197 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.1014. Min Act: -0.0000

Data Index: 1582265 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.2269. Min Act: -0.0000

Data Index: 371325 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 5.4439. Min Range: -5.4439

Max Act: 3.6623. Min Act: -0.0000

Data Index: 900505 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.1434. Min Act: -0.0000

Data Index: 1501727 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 5.4439. Min Range: -5.4439

Max Act: 3.7277. Min Act: -0.0000

Data Index: 480860 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 5.4439. Min Range: -5.4439

Max Act: 3.9439. Min Act: -0.0000

Data Index: 501981 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 5.4439. Min Range: -5.4439

Max Act: 3.4104. Min Act: -0.0000

Data Index: 265856 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 5.4439. Min Range: -5.4439

Max Act: 3.8521. Min Act: -0.0000

Data Index: 1215289 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 5.4439. Min Range: -5.4439

Max Act: 4.1529. Min Act: -0.0000

Data Index: 1139815 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 5.4439. Min Range: -5.4439

Max Act: 3.8224. Min Act: -0.0000

Data Index: 96853 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 5.4439. Min Range: -5.4439

Max Act: 3.6342. Min Act: -0.0000

Data Index: 671136 (C4 (Web Text))

Max Activating Token Index: 315