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

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

Neuron 3885 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: 2.3574. Min Range: -2.3574

Max Act: 2.3574. Min Act: -0.0000

Data Index: 1029461 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 2.3574. Min Range: -2.3574

Max Act: 2.1186. Min Act: -0.0000

Data Index: 209731 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 2.3574. Min Range: -2.3574

Max Act: 2.0372. Min Act: -0.0000

Data Index: 999567 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.6338. Min Act: -0.0000

Data Index: 379780 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.8014. Min Act: -0.0000

Data Index: 1252600 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 2.3574. Min Range: -2.3574

Max Act: 2.0109. Min Act: -0.0000

Data Index: 184432 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.7090. Min Act: -0.0000

Data Index: 629796 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.7531. Min Act: -0.0000

Data Index: 105725 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.6527. Min Act: -0.0000

Data Index: 91980 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.6149. Min Act: -0.0000

Data Index: 2558 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.5265. Min Act: -0.0000

Data Index: 171122 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.5633. Min Act: -0.0000

Data Index: 739710 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.5559. Min Act: -0.0000

Data Index: 146219 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.7535. Min Act: -0.0000

Data Index: 388486 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.5138. Min Act: -0.0000

Data Index: 596495 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.4590. Min Act: -0.0000

Data Index: 1160329 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.2764. Min Act: -0.0000

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.5473. Min Act: -0.0000

Data Index: 75920 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.4377. Min Act: -0.0000

Data Index: 373622 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.3574. Min Range: -2.3574

Max Act: 1.3767. Min Act: -0.0000

Data Index: 312941 (C4 (Web Text))

Max Activating Token Index: 849