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

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

Neuron 2422 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8799. Min Act: -0.0000

Data Index: 389826 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8451. Min Act: -0.0000

Data Index: 184209 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8339. Min Act: -0.0000

Data Index: 440627 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.8533. Min Act: -0.0000

Data Index: 482629 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7203. Min Act: -0.0000

Data Index: 655056 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7248. Min Act: -0.0000

Data Index: 458057 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7516. Min Act: -0.0000

Data Index: 390396 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7273. Min Act: -0.0000

Data Index: 770818 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6753. Min Act: -0.0000

Data Index: 534341 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.7153. Min Act: 0.0000

Data Index: 1123380 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6720. Min Act: -0.0000

Data Index: 665436 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6509. Min Act: -0.0000

Data Index: 743592 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6516. Min Act: -0.0000

Data Index: 659344 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6186. Min Act: -0.0000

Data Index: 249434 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1602263 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1024320 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6413. Min Act: 0.0000

Data Index: 153598 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6000. Min Act: -0.0000

Data Index: 64436 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.6178. Min Act: 0.0000

Data Index: 196713 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.8799. Min Range: -0.8799

Max Act: 0.5725. Min Act: -0.0000

Data Index: 424774 (C4 (Web Text))

Max Activating Token Index: 390