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

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

Neuron 3033 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7296. Min Act: -0.0001

Data Index: 1018006 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7585. Min Act: -0.0001

Data Index: 425510 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7177. Min Act: -0.0001

Data Index: 597224 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7000. Min Act: -0.0001

Data Index: 209991 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6812. Min Act: -0.0001

Data Index: 614013 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6842. Min Act: -0.0001

Data Index: 473938 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6794. Min Act: -0.0001

Data Index: 620096 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6931. Min Act: -0.0001

Data Index: 920439 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6662. Min Act: -0.0001

Data Index: 394296 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6672. Min Act: -0.0001

Data Index: 368739 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6912. Min Act: -0.0001

Data Index: 211533 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6555. Min Act: -0.0001

Data Index: 367109 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6713. Min Act: -0.0001

Data Index: 705073 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6630. Min Act: -0.0001

Data Index: 370587 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6802. Min Act: -0.0001

Data Index: 1215650 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6289. Min Act: -0.0001

Data Index: 721442 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6526. Min Act: -0.0001

Data Index: 1246489 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6484. Min Act: -0.0001

Data Index: 684877 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1059233 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1322031 (C4 (Web Text))

Max Activating Token Index: 194