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

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

Neuron 4071 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0389. Min Range: -1.0389

Max Act: 1.0296. Min Act: -0.0001

Data Index: 88419 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9881. Min Act: -0.0001

Data Index: 1083333 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9953. Min Act: -0.0001

Data Index: 1176519 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.0389. Min Range: -1.0389

Max Act: 1.0198. Min Act: -0.0001

Data Index: 684523 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9824. Min Act: -0.0001

Data Index: 738206 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 1.0389. Min Range: -1.0389

Max Act: 1.0389. Min Act: -0.0001

Data Index: 333448 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9671. Min Act: -0.0001

Data Index: 57961 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9667. Min Act: -0.0001

Data Index: 1130984 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.0389. Min Range: -1.0389

Max Act: 1.0047. Min Act: -0.0001

Data Index: 108906 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9448. Min Act: -0.0001

Data Index: 855220 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9664. Min Act: -0.0001

Data Index: 1271130 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9619. Min Act: -0.0001

Data Index: 104483 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9275. Min Act: -0.0001

Data Index: 815728 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9759. Min Act: -0.0001

Data Index: 969835 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9494. Min Act: -0.0001

Data Index: 704483 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9517. Min Act: -0.0001

Data Index: 1353899 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9105. Min Act: -0.0001

Data Index: 981990 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9680. Min Act: -0.0001

Data Index: 706851 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9320. Min Act: -0.0001

Data Index: 235179 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8482. Min Act: -0.0001

Data Index: 1235991 (C4 (Web Text))

Max Activating Token Index: 203