Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2011 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8890. Min Act: -0.0003

Data Index: 742982 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8703. Min Act: -0.0003

Data Index: 1179354 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8656. Min Act: -0.0003

Data Index: 75471 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7906. Min Act: -0.0003

Data Index: 940211 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8333. Min Act: -0.0003

Data Index: 169685 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8298. Min Act: -0.0003

Data Index: 1052397 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8001. Min Act: -0.0003

Data Index: 991970 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8831. Min Act: -0.0003

Data Index: 906221 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8236. Min Act: -0.0003

Data Index: 985713 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8247. Min Act: -0.0003

Data Index: 1199816 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7941. Min Act: -0.0003

Data Index: 1166660 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7937. Min Act: -0.0003

Data Index: 959584 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8143. Min Act: -0.0003

Data Index: 986481 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7618. Min Act: -0.0003

Data Index: 1100501 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8053. Min Act: -0.0003

Data Index: 966947 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7507. Min Act: -0.0003

Data Index: 929159 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7998. Min Act: -0.0003

Data Index: 1272652 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8008. Min Act: -0.0003

Data Index: 1005302 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7501. Min Act: -0.0003

Data Index: 1023248 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7733. Min Act: -0.0003

Data Index: 768977 (C4 (Web Text))

Max Activating Token Index: 106