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

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

Neuron 2619 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: 0.1780. Min Range: -0.1780

Max Act: 0.1780. Min Act: -0.0001

Data Index: 1051385 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1672. Min Act: -0.0001

Data Index: 918225 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1606. Min Act: -0.0001

Data Index: 244124 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1610. Min Act: -0.0001

Data Index: 65710 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1538. Min Act: -0.0001

Data Index: 275083 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1568. Min Act: -0.0001

Data Index: 641722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1561. Min Act: -0.0001

Data Index: 758553 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1518. Min Act: -0.0001

Data Index: 109486 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1508. Min Act: -0.0001

Data Index: 28212 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1524. Min Act: -0.0001

Data Index: 414480 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1488. Min Act: -0.0001

Data Index: 643637 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1056428 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1478. Min Act: -0.0001

Data Index: 26978 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1482. Min Act: -0.0001

Data Index: 833723 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1088384 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1357445 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1038255 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1431. Min Act: -0.0001

Data Index: 16834 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1453. Min Act: -0.0001

Data Index: 464726 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1424. Min Act: -0.0001

Data Index: 690826 (C4 (Web Text))

Max Activating Token Index: 384