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

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

Neuron 4889 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.9042. Min Act: -0.0000

Data Index: 357705 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.7471. Min Act: -0.0000

Data Index: 63476 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6450. Min Act: -0.0000

Data Index: 605039 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6361. Min Act: -0.0000

Data Index: 310685 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5549. Min Act: -0.0000

Data Index: 679993 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1220310 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.6069. Min Act: -0.0000

Data Index: 974828 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5720. Min Act: -0.0000

Data Index: 440678 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5354. Min Act: -0.0000

Data Index: 335219 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1277997 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4929. Min Act: -0.0000

Data Index: 679724 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4738. Min Act: -0.0000

Data Index: 81959 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1091019 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4778. Min Act: -0.0000

Data Index: 346400 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.5054. Min Act: -0.0000

Data Index: 999112 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1359636 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1209876 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4586. Min Act: -0.0000

Data Index: 61055 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4853. Min Act: -0.0000

Data Index: 918268 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.9042. Min Range: -0.9042

Max Act: 0.4356. Min Act: -0.0000

Data Index: 152366 (C4 (Web Text))

Max Activating Token Index: 438