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

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

Neuron 4778 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.8467. Min Act: -0.0000

Data Index: 691692 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6766. Min Act: -0.0000

Data Index: 178604 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1151065 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6146. Min Act: -0.0000

Data Index: 728820 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5984. Min Act: -0.0000

Data Index: 789027 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1147665 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5365. Min Act: -0.0000

Data Index: 877956 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5717. Min Act: -0.0000

Data Index: 632627 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1020124 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5631. Min Act: -0.0000

Data Index: 394337 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5222. Min Act: -0.0000

Data Index: 195175 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5180. Min Act: -0.0000

Data Index: 177242 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1036503 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5179. Min Act: -0.0000

Data Index: 323059 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.4930. Min Act: -0.0000

Data Index: 440870 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5230. Min Act: -0.0000

Data Index: 246580 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.4905. Min Act: -0.0000

Data Index: 227579 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5074. Min Act: -0.0000

Data Index: 76265 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5016. Min Act: -0.0000

Data Index: 657930 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.4859. Min Act: -0.0000

Data Index: 535091 (C4 (Web Text))

Max Activating Token Index: 118