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

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

Neuron 4825 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2538. Min Range: -2.2538

Max Act: 2.2538. Min Act: -0.0000

Data Index: 437244 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.2538. Min Range: -2.2538

Max Act: 1.5729. Min Act: -0.0000

Data Index: 753537 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 2.2538. Min Range: -2.2538

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1285600 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 2.2538. Min Range: -2.2538

Max Act: 1.3310. Min Act: -0.0000

Data Index: 462881 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 2.2538. Min Range: -2.2538

Max Act: 1.1806. Min Act: -0.0000

Data Index: 996638 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1295547 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 2.2538. Min Range: -2.2538

Max Act: 1.0743. Min Act: -0.0000

Data Index: 483336 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 2.2538. Min Range: -2.2538

Max Act: 1.0571. Min Act: -0.0000

Data Index: 157962 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9949. Min Act: -0.0000

Data Index: 376986 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9758. Min Act: -0.0000

Data Index: 781902 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 2.2538. Min Range: -2.2538

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1038244 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1313530 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9672. Min Act: -0.0000

Data Index: 101993 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9599. Min Act: -0.0000

Data Index: 372667 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9450. Min Act: -0.0000

Data Index: 725950 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9368. Min Act: -0.0000

Data Index: 709693 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.8793. Min Act: -0.0000

Data Index: 105300 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9774. Min Act: -0.0000

Data Index: 370138 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1223800 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 2.2538. Min Range: -2.2538

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1215917 (C4 (Web Text))

Max Activating Token Index: 34