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

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

Neuron 3778 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.4817. Min Act: -0.0000

Data Index: 519933 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1132. Min Act: -0.0000

Data Index: 634830 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1405. Min Act: -0.0000

Data Index: 402187 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1310960 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.9750. Min Act: -0.0000

Data Index: 508532 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.5372. Min Act: -0.0000

Data Index: 29406 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.4274. Min Act: -0.0000

Data Index: 610609 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1277699 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.3822. Min Act: -0.0000

Data Index: 77490 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.3896. Min Act: -0.0000

Data Index: 844763 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.3728. Min Act: -0.0000

Data Index: 761445 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.2851. Min Act: -0.0000

Data Index: 829435 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.2924. Min Act: -0.0000

Data Index: 499151 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1106156 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.3099. Min Act: -0.0000

Data Index: 768111 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.2711. Min Act: -0.0000

Data Index: 851075 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.3348. Min Act: -0.0000

Data Index: 261065 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1047852 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.3409. Min Act: -0.0000

Data Index: 373004 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1353521 (C4 (Web Text))

Max Activating Token Index: 589