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

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

Neuron 3513 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0439. Min Range: -1.0439

Max Act: 1.0439. Min Act: -0.0000

Data Index: 954929 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.8236. Min Act: -0.0000

Data Index: 257721 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1045522 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5874. Min Act: -0.0000

Data Index: 899496 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6157. Min Act: -0.0000

Data Index: 734670 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1054638 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1201690 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5479. Min Act: -0.0000

Data Index: 823161 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5511. Min Act: -0.0000

Data Index: 846159 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1621200 (Python Code)

Max Activating Token Index: 735

Text #10

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5065. Min Act: -0.0000

Data Index: 670370 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5130. Min Act: -0.0000

Data Index: 666464 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5113. Min Act: -0.0000

Data Index: 570169 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5407. Min Act: -0.0000

Data Index: 853580 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.4725. Min Act: -0.0000

Data Index: 424882 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5125. Min Act: -0.0000

Data Index: 24979 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.5139. Min Act: -0.0000

Data Index: 257587 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.4933. Min Act: -0.0000

Data Index: 871556 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.4542. Min Act: -0.0000

Data Index: 54829 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.4609. Min Act: -0.0000

Data Index: 650183 (C4 (Web Text))

Max Activating Token Index: 692