Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6616. Min Act: -0.0001

Data Index: 557026 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7765. Min Act: -0.0001

Data Index: 359837 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7563. Min Act: -0.0001

Data Index: 1294981 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7444. Min Act: -0.0001

Data Index: 103763 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7635. Min Act: -0.0001

Data Index: 155066 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6976. Min Act: -0.0001

Data Index: 1099065 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.5918. Min Act: -0.0001

Data Index: 9811 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7102. Min Act: -0.0001

Data Index: 680671 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1318662 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6548. Min Act: -0.0001

Data Index: 479999 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7772. Min Act: -0.0001

Data Index: 912334 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6688. Min Act: -0.0001

Data Index: 1041540 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6959. Min Act: -0.0001

Data Index: 460332 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6980. Min Act: -0.0001

Data Index: 876715 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7365. Min Act: -0.0001

Data Index: 1275089 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6364. Min Act: -0.0001

Data Index: 479765 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6657. Min Act: -0.0001

Data Index: 329582 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.7564. Min Act: -0.0001

Data Index: 524697 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6173. Min Act: -0.0001

Data Index: 778139 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.7772. Min Range: -0.7772

Max Act: 0.6230. Min Act: -0.0001

Data Index: 976357 (C4 (Web Text))

Max Activating Token Index: 454