Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1205 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2860. Min Range: -1.2860

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1268525 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1122039 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.7652. Min Act: -0.0000

Data Index: 621164 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.6764. Min Act: -0.0000

Data Index: 525683 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1056077 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.6207. Min Act: -0.0000

Data Index: 216085 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.6003. Min Act: -0.0000

Data Index: 699627 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.6126. Min Act: -0.0000

Data Index: 941033 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5732. Min Act: -0.0000

Data Index: 906676 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5452. Min Act: -0.0000

Data Index: 409557 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5732. Min Act: -0.0000

Data Index: 278962 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5361. Min Act: -0.0000

Data Index: 149176 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5135. Min Act: -0.0000

Data Index: 685510 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5471. Min Act: -0.0000

Data Index: 472369 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1341817 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5110. Min Act: -0.0000

Data Index: 396265 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5023. Min Act: -0.0000

Data Index: 598185 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5167. Min Act: -0.0000

Data Index: 212954 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.5123. Min Act: -0.0000

Data Index: 757948 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.2860. Min Range: -1.2860

Max Act: 0.4943. Min Act: -0.0000

Data Index: 12249 (C4 (Web Text))

Max Activating Token Index: 417