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

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

Neuron 5882 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: 0.6956. Min Range: -0.6956

Max Act: 0.6896. Min Act: -0.0000

Data Index: 693318 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6316. Min Act: -0.0000

Data Index: 455599 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6956. Min Act: -0.0000

Data Index: 259463 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6734. Min Act: -0.0000

Data Index: 656736 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6446. Min Act: -0.0000

Data Index: 974384 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6576. Min Act: -0.0000

Data Index: 620147 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1121837 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6007. Min Act: -0.0000

Data Index: 4373 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1100921 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6089. Min Act: -0.0000

Data Index: 60377 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6031. Min Act: -0.0000

Data Index: 506733 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6059. Min Act: -0.0000

Data Index: 111452 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6033. Min Act: -0.0000

Data Index: 774013 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5568. Min Act: -0.0000

Data Index: 729041 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1005116 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5799. Min Act: -0.0000

Data Index: 736120 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5636. Min Act: -0.0000

Data Index: 193266 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1310242 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5531. Min Act: -0.0000

Data Index: 809339 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5319. Min Act: -0.0000

Data Index: 12658 (C4 (Web Text))

Max Activating Token Index: 890