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

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

Neuron 2426 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: 0.1202. Min Range: -0.1202

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1189246 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0928. Min Act: -0.0000

Data Index: 513031 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1094881 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0900. Min Act: -0.0000

Data Index: 543890 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0933. Min Act: -0.0001

Data Index: 741839 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0867. Min Act: -0.0001

Data Index: 712035 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0892. Min Act: -0.0000

Data Index: 120615 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1165745 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1119364 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0815. Min Act: -0.0001

Data Index: 664499 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0858. Min Act: -0.0001

Data Index: 769787 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0797. Min Act: -0.0001

Data Index: 510079 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0827. Min Act: -0.0001

Data Index: 71743 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0824. Min Act: -0.0001

Data Index: 931616 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1275651 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0810. Min Act: -0.0001

Data Index: 620627 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0861. Min Act: -0.0001

Data Index: 770984 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0795. Min Act: -0.0001

Data Index: 679467 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0797. Min Act: -0.0000

Data Index: 33303 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0763. Min Act: -0.0000

Data Index: 197388 (C4 (Web Text))

Max Activating Token Index: 301