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

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

Neuron 83 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: 1.4573. Min Range: -1.4573

Max Act: 1.4573. Min Act: -0.0000

Data Index: 137098 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.4573. Min Range: -1.4573

Max Act: 1.1342. Min Act: -0.0000

Data Index: 884926 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 1.4573. Min Range: -1.4573

Max Act: 1.1899. Min Act: -0.0000

Data Index: 113327 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 1.4573. Min Range: -1.4573

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1165502 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.4573. Min Range: -1.4573

Max Act: 1.1410. Min Act: -0.0000

Data Index: 611341 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 1.4573. Min Range: -1.4573

Max Act: 1.0213. Min Act: -0.0000

Data Index: 256565 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.9800. Min Act: -0.0000

Data Index: 665497 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.8431. Min Act: -0.0000

Data Index: 172718 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.7710. Min Act: -0.0000

Data Index: 405186 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.7900. Min Act: -0.0000

Data Index: 665918 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.7807. Min Act: -0.0000

Data Index: 963846 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.7134. Min Act: -0.0000

Data Index: 784402 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.7017. Min Act: -0.0000

Data Index: 177720 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6922. Min Act: -0.0000

Data Index: 886941 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6421. Min Act: -0.0000

Data Index: 243576 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6694. Min Act: -0.0000

Data Index: 519213 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1240684 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6673. Min Act: -0.0000

Data Index: 795167 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1397625 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6154. Min Act: -0.0000

Data Index: 129213 (C4 (Web Text))

Max Activating Token Index: 346